Register for free to join our community of investors and share your ideas. You will also get access to streaming quotes, interactive charts, trades, portfolio, live options flow and more tools.
bitcoin mining was/is a means to obtain the results for the library function to calibrate a quantum computer? wags.
so all this time, bit coin miners owe us vcsy shareholders some coin?
and the old vcsy webpage showing siteflash/response flash was /is included in the ploinks/puddle paradigm. wags.
back to the future.
rpi now has a quantum system one supercomputer.....gpu's from nvida....connect those babies and blam rings of power?
jia tan a linux developer seems implicated in a linux server hack to open back door the internet....this might help the newest 8 patent and v ip? wags. it was thwarted by a german msft employee doing a routine test on software? this would seem to be a war scenario if tan could be connected to china or noko or russia or other? if we've got to profit from conflict it might as well be vcsy/8 and make money from the fix?
8 newest patent of 3 days ago:me looking at 4/2/2024 8 patent...."programming/data sets via a data communications server. or would seem to be how/what are the programmable apis of the chat app/s. scipts written in a rogramming language that includes routing and/or call flow commands." They say,'the server is to execute the set of scripts to retrieve data from the data sources and control, in response to the data, call flow for the calls. '
me: this seems to include executable instructions as in a processor/remote equipment/robot/automated process?
segue with v ip.....first to the second computing device. voila.
Certainly! Let’s delve into the fascinating world of stochastic randomness and its connection to memristors.
Memristors and Stochastic Behavior:
Memristive devices exhibit intriguing properties, including resistive switching effects. These effects arise due to the stochastic nature of filament formation during resistance switching.
When a single filament growth dominates, the switching behavior becomes fully random, following a Poissonian distribution. In other words, the switching time is inherently stochastic and shows a broad distribution1.
Despite this apparent randomness, researchers have discovered that the supposed randomness can be well characterized and controlled. Memristors, with their native stochastic characteristic, can be harnessed for novel computing schemes.
Stochastic Computing:
Instead of using inherently non-deterministic memristor devices for deterministic applications (such as digital memory storage), we can explore a hybrid CMOS-memristor architecture.
In this hybrid setup, the randomness inherent in memristors enables more efficient and error-tolerant computing. By leveraging the stochastic switching events, we can create predictable biases and generate random bit streams for specific computational tasks1.
Applications and Challenges:
Memristors are promising candidates for future non-volatile memory technology due to their scalability, endurance, and low power consumption.
However, the large variations in switching parameters pose challenges for mainstream manufacturing and commercialization.
Addressing these variations and understanding the stochastic behavior of memristors is crucial for unlocking their full potential in computing and neuromorphic applications12.
In summary, memristors, with their inherent stochasticity, offer exciting possibilities for unconventional computing paradigms. By embracing randomness, we can create more efficient and robust system
memristors and stochastic randomness?
"Certainly! Let’s delve into the fascinating world of memristors and their connection to high-bandwidth memory.
Memristors: A Brief Overview
Memristors are intriguing electronic devices that exhibit a unique property: their resistance can be altered by the flow of electric charge. Here are some key points about memristors:
Definition: A memristor is a two-terminal passive electronic component that can “remember” its resistance state even after the power is turned off.
Switching Mechanisms: Memristors can switch between high and low resistance states based on various physical mechanisms, such as barrier modification, photo-induced molecular switching, and interactions with nanoscale conductive filaments.
Applications:
Non-Volatile Memory: Memristors are known for their low-power, non-volatile memory operation. They can store information for relatively long periods.
Neuromorphic Computing: These devices can emulate the switching and learning properties of biological synapses. As a result, they hold promise for creating bio-inspired neuromorphic computing systems.
Optical Memristors: Recently, there has been a push to develop memristor devices that can be controlled by light. Integrating non-volatile electronic memory with high-speed optical signaling opens up exciting possibilities in optical telecommunications and photonic computing1.
High-Bandwidth Memory (HBM)
High-Bandwidth Memory (HBM) is a type of memory architecture designed for high-performance computing and graphics applications. Here are the key features of HBM:
Stacked Design: HBM stacks multiple memory dies vertically, creating a 3D structure. This stacking allows for significantly higher memory bandwidth compared to traditional memory architectures.
Wide Data Bus: HBM uses a wide data bus (up to 1024 bits) to transfer data between the memory and the processor. This wide bus enables high-speed data communication.
High Bandwidth: HBM achieves exceptional bandwidth by minimizing the distance between the memory cells and the processor. This proximity reduces latency and enhances data transfer rates.
Applications:
Graphics Cards: HBM is commonly used in high-end graphics cards (GPUs) for gaming, video editing, and scientific simulations.
AI and Machine Learning: HBM’s high bandwidth is crucial for accelerating AI and machine learning workloads.
Supercomputers: HBM is also employed in supercomputers and data centers for scientific simulations and data-intensive tasks.
The Intersection of Memristors and HBM
The integration of optical memristors with high-speed and high-bandwidth optical signaling provides an exciting platform for future applications. Here’s why:
Optical Memristors: These memristors can be controlled by light, making them suitable for use in optical telecommunications and photonic computing.
Neuromorphic Computing: Combining memristors with HBM could lead to powerful neuromorphic computing systems that mimic the brain’s self-organized, adaptive properties.
AI and Big Data: As we enter the era of post von Neumann computing, the demand for increased computational power (for AI, the Internet of Things, and Big Data) makes this integration even more relevant12.
In summary, memristors and HBM represent cutting-edge developments in memory technology. Their convergence holds immense potential for advancing computing, communication, and artificial intelligence. 🌟"copilot says.
3dxp and robotics/remote work...infrared laser communications and lunar/mars work. stochastic randomness..a confusion of words......? on purpose to throw off the ai searches? it's not intuitive.
75 crossbar arrays....and two layers....2d with another d....duh, 3d xp...intel and micron.........v ip and 8 x8. wags.
vip secure personal space/place; the needle in the haystacks!
we are going to be ..............fill in the blank. however, what a world mess we will receive our gift in......
iran threatening our existence as helpers of israel. our own president seems to be vacillating in his support for our allies.
the hamas strategy of human shields is working this time with their cheer leaders within our own government and populace.
this is better than the threat of nuclear or biologics....like the comedy skits where the culprit holds the gun to his head and threatens to shoot himself if you don't surrender.. it is so obvious. israel obviously sees thru this and it didn't help the zealots of israeli lore. the romans didn't care or felt it was the cost of doing business. the problem for the world is that their leadership , themselves, live in qatar in lavish surroundings and are not injured in anyway. we actually send them more money at our expense. i think we need some adults in the room to put the leverage where it's needed. it ain't gaze which is a propaganda coup beyond their imagination. wags.
In the study, the team programmed a Bayesian neural network on an assembly of 75 crossbar arrays, each containing 1,024 memristors, complemented by CMOS periphery for in-memory computing. The experiment involved a two-layer Bayesian neural network trained to differentiate nine classes of heart arrhythmia from electrocardiogram (ECG) recordings.
The experimental results were compelling, with the memristor-based Bayesian neural network nearly matching the best performances of a software neural network in terms of both aleatoric (area under the curve of 0.91) and epistemic uncertainty evaluation (area under the curve of 0.99), albeit with a slight reduction in raw accuracy. This performance sharply contrasted conventional neural networks, which exhibit little ability to recognize unknown data and evaluate uncertainties.
That’s amazing stuff! Now add these new memristors to quantum computers , LLM’s and AI. Bam!
but recognition of the object in different 'circumstances' is found. recognizing objects in images...?
today, msft disconnected msft teams from msft 365...like it did for eu..........other sovereign data countries likely want the same?
fortunately, 8x8 work allows multiple chat apps in the app with programmable apis.
multiple chat apps might have some different names for the same objects? for tunately , there is v ip stochastic randomness qualities in objects. wags.
so, at least msft, if not google, amazon, oracle , and the rest follow suit. i hope. i think , we're almost there.
A stochastic process can have many outcomes, due to its randomness, and a single outcome of a stochastic process is called, among other names, a sample function or realization.[28
Doc. Yes. And my key takeaway from this article…
This performance sharply contrasted conventional neural networks, which exhibit little ability to recognize unknown data and evaluate uncertainties.
Hmmm The ability to recognize unknown data and. …. Wait for it… “evaluate uncertainties “. Or Arbitrary objects!
Like I said before. The Tec is finally catching up to our patent..
or, how to define an object... it ain't borland delphi arbitrary object. it's arbitrary object in the manner of vcsy and said framework.
they could make the subject matter more clear with better choice of 'words' to describe the phenomenon? guesses.
Introduction
A stochastic or random process can be defined as a collection of random variables that is indexed by some mathematical set, meaning that each random variable of the stochastic process is uniquely associated with an element in the set.[4][5] The set used to index the random variables is called the index set. Historically, the index set was some subset of the real line, such as the natural numbers, giving the index set the interpretation of time.[1] Each random variable in the collection takes values from the same mathematical space known as the state space. This state space can be, for example, the integers, the real line or
?
{\displaystyle n}-dimensional Euclidean space.[1][5] An increment is the amount that a stochastic process changes between two index values, often interpreted as two points in time.[48][49] A stochastic process can have many outcomes, due to its randomness, and a single outcome of a stochastic process is called, among other names, a sample function or realization.[28
Chinese scientists unlock potential of memristor semiconductor building block that could boost artificial intelligence, self-driving cars and more
World’s first fully system-integrated memristor chip could make artificial intelligence smarter and up to 75 times more efficient, researchers say
Advances could lead to AI that is capable of more human-like learning, with implications for how smart devices and autonomous driving work
Topic | Science
Follow this topic and get notified the next time we publish content about Science.
Victoria Bela
Victoria Bela
Published: 10:07pm, 11 Oct, 2023
The world’s first fully system-integrated memristor chip has been unveiled by a team of Chinese scientists who believe it could not only make artificial intelligence smarter, but also more time and energy efficient. While the semiconductor has yet to leave the lab setting, it could allow for the development of AI that is capable of more human-like learning, which could have implications for the way smart devices and autonomous driving work, according to the researchers. “Learning is highly important,” for edge intelligence devices, the research team from Tsinghua University said in their study released in the journal Science on September 15, referencing devices that process data internally with technology like AI. The advancement is the latest in a series of Chinese semiconductor innovations announced since US-imposed export controls and sanctions restricted the supply of advanced chips and chip-making equipment to the nation.
Advertisement
Advertisement
The development of a new microchip announced last month by Huawei made a splash in the media, and called into question whether China had the expertise to advance semiconductors without US technology. China’s new memristor chip is a significant step forward in developing such technology, according to the researchers.
“Memristor-based computing technology has recently received considerable attention because of its potential to overcome the so-called ‘von Neumann bottleneck’ of conventional computing architecture,” Yury Suleymanov, an associate editor at Science, said in his editor’s summary of the paper, referring to the computational limitation set by the separation of memory and processing.
China At A Glance
By submitting, you consent to receiving marketing emails from SCMP. If you don't want these, tick here
SIGN UP
By registering, you agree to our T&C and Privacy Policy
A resistor is an element of a circuit that is able to limit the flow of energy by providing resistance to electrons flowing through.
China downplays reports of Taiwanese firms helping Huawei’s semiconductor ambitions
11 Oct 2023
A memristor – a contraction for memory resistor – is able to remember the most recent value of current that was passed through it when it was turned on, meaning future resistance can depend on prior history, according to Nature Electronics. As such, it is capable of improvement-based learning, or maintaining pre-acquired knowledge when something new is learned.
This differs from transfer learning, which focuses on moving to a new set of data and can sacrifice the accuracy of prior data, according to the paper. To train artificial neural networks, which mimic how human neurons pass on data in the brain, conventional hardware requires a great deal of energy and time to move data between the computing and memory units.
The study is an important step towards future chips with high energy efficiency and extensive learning capabilities
Wu Huaqiang and Gao Bin
Memristor-based computing is able to reduce the energy required for a task by allowing the learning to occur on-chip with no external memory source.
Several studies have investigated memristors, but they still used additional external processors, the team said in their paper. The researchers produced a chip capable of conducting complete on-chip improvement learning, and proposed a learning architecture for it.
They said they were able to demonstrate on-chip learning with multiple tasks, including image classification, motion control, and audio recognition.
How artificial intelligence will redefine the future of work
20 Jun 2022
In one demonstration, the motion control of a model car designed to pursue a laser light was better at finding the light in a dark environment and would lose track of it in a brighter environment. But after implementing learning, it was able to find the light equally well in both environments.
The accuracy in the bright environment greatly increased, while accuracy in the dark environment did not decrease with the addition of the new ability. “The memristor-based neuro-inspired computing chip could facilitate the development of edge AI devices that could adapt to new scenes and users,” the researchers said in their paper.
With further research on the learning architecture, the team said it believed it could enable on-chip learning that is 75 times more energy efficient than current machines designed for AI processing.
Still, challenges remain in the research and development of such chips – in particular, engineering the chips for large-scale integration. It could take time for the technology to make it out of the laboratory, Wu Huaqiang and Gao Bin, professors at Tsinghua and leads of the research team, admitted to Chinese-language news site Science Times. “The study is an important step towards future chips with high energy efficiency and extensive learning capabilities,” the researchers said, adding they hoped their findings “will accelerate the development of future smart edge devices”
International Researchers Move the Needle on Memristor Technology
December 19, 2023 by Jake Hertz
Academics across the globe have made concurrent breakthroughs in a new form of non-volatile memory.
Memristors, or memory resistors, are an emerging form of non-volatile memory considered a viable alternative to traditional memory storage. These devices act as switches that can recall their electric state even after their power is turned off, allowing them to behave like human neurons—both computing and storing data.
Memristors are a hot research topic for their numerous unique properties, including scalability to lower process nodes, which enable smaller, faster, and more energy-efficient devices.
Cea-Leti's wafer-level memristor crossbar arrays
Cea-Leti's wafer-level memristor crossbar arrays using a prober. Image (modified) used courtesy of Cea-Leti
Now, as the demand for more sophisticated and power-efficient computing grows, memristors hold promise in various applications, including artificial intelligence, neuromorphic computing, and high-density data storage. In recent months, several international research teams have published findings about memristors that may help push this technology from lab to market.
The University of Rochester: Strain-Engineered Phase-Change Memristors
Researchers at the University of Rochester recently developed high-performance, bipolar phase-change memristors based on strain-engineered multilayer molybdenum ditelluride (MoTe2).
The strain-based memristor
The strain-based memristor. Image used courtesy of Nature
These devices, distinguished by their bipolar phase-change characteristics, represent a significant leap from conventional filamentary conduction mechanisms. The study successfully utilizes process-induced strain engineering to induce a semimetallic-to-semiconducting phase transition in MoTe2.
This transition is key to achieving the memristor's remarkable switching characteristics, including low voltages of 90 mV, high on/off ratios of 10^8, swift switching times of 5 ns, and prolonged retentions over 10^5 seconds. Such performance metrics indicate the potential of these memristors for applications in robust, fast, low-power, and scalable memory and neuromorphic computing systems.
The device's performance can also be finely tuned by varying a single process parameter: the contact metal film force, a product of film stress and thickness. This control over the device's switching voltage and on/off ratio underlines the memristor's adaptability and potential for diverse applications.
Cea-Leti: Using Memristors for Bayesian Neural Networks
In France, a group of Cea-Leti researchers announced that they have successfully integrated memristor hardware into artificial intelligence systems. Specifically, the team leveraged the inherent probabilistic nature of memristors to effectively execute the computationally intensive tasks of Bayesian neural networks.
Filamentary memristor
Filamentary memristor in the back end of the line of Cea-Leti's hybrid memristor/CMOS process. Image used courtesy of Nature
In the study, the team programmed a Bayesian neural network on an assembly of 75 crossbar arrays, each containing 1,024 memristors, complemented by CMOS periphery for in-memory computing. The experiment involved a two-layer Bayesian neural network trained to differentiate nine classes of heart arrhythmia from electrocardiogram (ECG) recordings.
The experimental results were compelling, with the memristor-based Bayesian neural network nearly matching the best performances of a software neural network in terms of both aleatoric (area under the curve of 0.91) and epistemic uncertainty evaluation (area under the curve of 0.99), albeit with a slight reduction in raw accuracy. This performance sharply contrasted conventional neural networks, which exhibit little ability to recognize unknown data and evaluate uncertainties.
Tsinghua University: 2D-Material-Based Memristors
Finally, in China, a team at Tsinghua University developed a new system-integrated memristor computing-in-memory chip the researchers claim is the world's first of its kind to support efficient on-chip learning. This chip, still in the laboratory phase, is expected to significantly advance developments in fields such as artificial intelligence, autonomous driving, and wearable devices, among others
The memristor-based integrated circuit
The memristor-based integrated circuit. Image used courtesy of Tsinghua University
The chip is notably energy efficient, consuming only 3% of the energy of an application-specific integrated circuit (ASIC) system for on-chip learning. According to the team, this innovation started with research on memristors for storage applications and took about 11 years to develop to this point.
Memristors Gain International Steam
Memristors converge computing and memory within a single device, opening up new frontiers for energy-efficient, high-speed, and intelligent computing solutions. As international researchers continue to explore and refine memristor technology, they pave the way for more advanced and efficient computing systems that could define the next generation of electronics.
International Researchers Move the Needle on Memristor Technology
December 19, 2023 by Jake Hertz
Academics across the globe have made concurrent breakthroughs in a new form of non-volatile memory.
Memristors, or memory resistors, are an emerging form of non-volatile memory considered a viable alternative to traditional memory storage. These devices act as switches that can recall their electric state even after their power is turned off, allowing them to behave like human neurons—both computing and storing data.
Memristors are a hot research topic for their numerous unique properties, including scalability to lower process nodes, which enable smaller, faster, and more energy-efficient devices.
Cea-Leti's wafer-level memristor crossbar arrays
Cea-Leti's wafer-level memristor crossbar arrays using a prober. Image (modified) used courtesy of Cea-Leti
Now, as the demand for more sophisticated and power-efficient computing grows, memristors hold promise in various applications, including artificial intelligence, neuromorphic computing, and high-density data storage. In recent months, several international research teams have published findings about memristors that may help push this technology from lab to market.
The University of Rochester: Strain-Engineered Phase-Change Memristors
Researchers at the University of Rochester recently developed high-performance, bipolar phase-change memristors based on strain-engineered multilayer molybdenum ditelluride (MoTe2).
The strain-based memristor
The strain-based memristor. Image used courtesy of Nature
These devices, distinguished by their bipolar phase-change characteristics, represent a significant leap from conventional filamentary conduction mechanisms. The study successfully utilizes process-induced strain engineering to induce a semimetallic-to-semiconducting phase transition in MoTe2.
This transition is key to achieving the memristor's remarkable switching characteristics, including low voltages of 90 mV, high on/off ratios of 10^8, swift switching times of 5 ns, and prolonged retentions over 10^5 seconds. Such performance metrics indicate the potential of these memristors for applications in robust, fast, low-power, and scalable memory and neuromorphic computing systems.
The device's performance can also be finely tuned by varying a single process parameter: the contact metal film force, a product of film stress and thickness. This control over the device's switching voltage and on/off ratio underlines the memristor's adaptability and potential for diverse applications.
Cea-Leti: Using Memristors for Bayesian Neural Networks
In France, a group of Cea-Leti researchers announced that they have successfully integrated memristor hardware into artificial intelligence systems. Specifically, the team leveraged the inherent probabilistic nature of memristors to effectively execute the computationally intensive tasks of Bayesian neural networks.
Filamentary memristor
Filamentary memristor in the back end of the line of Cea-Leti's hybrid memristor/CMOS process. Image used courtesy of Nature
In the study, the team programmed a Bayesian neural network on an assembly of 75 crossbar arrays, each containing 1,024 memristors, complemented by CMOS periphery for in-memory computing. The experiment involved a two-layer Bayesian neural network trained to differentiate nine classes of heart arrhythmia from electrocardiogram (ECG) recordings.
The experimental results were compelling, with the memristor-based Bayesian neural network nearly matching the best performances of a software neural network in terms of both aleatoric (area under the curve of 0.91) and epistemic uncertainty evaluation (area under the curve of 0.99), albeit with a slight reduction in raw accuracy. This performance sharply contrasted conventional neural networks, which exhibit little ability to recognize unknown data and evaluate uncertainties.
Tsinghua University: 2D-Material-Based Memristors
Finally, in China, a team at Tsinghua University developed a new system-integrated memristor computing-in-memory chip the researchers claim is the world's first of its kind to support efficient on-chip learning. This chip, still in the laboratory phase, is expected to significantly advance developments in fields such as artificial intelligence, autonomous driving, and wearable devices, among others
The memristor-based integrated circuit
The memristor-based integrated circuit. Image used courtesy of Tsinghua University
The chip is notably energy efficient, consuming only 3% of the energy of an application-specific integrated circuit (ASIC) system for on-chip learning. According to the team, this innovation started with research on memristors for storage applications and took about 11 years to develop to this point.
Memristors Gain International Steam
Memristors converge computing and memory within a single device, opening up new frontiers for energy-efficient, high-speed, and intelligent computing solutions. As international researchers continue to explore and refine memristor technology, they pave the way for more advanced and efficient computing systems that could define the next generation of electronics.
This part stuck out.
“The scientists rewrote Bayesian equations so a memristor array could perform statistical analyses that harnesses randomness—a.k.a. “stochastic computing.”
“That harness randomness”. ?
Or arbitrary objects?
744/629 is very,very valuable. Wouldn’t you agree Doc? All the pieces seem to be finally catching up to the patent. Now, the more breakthroughs with memristors, the more valuable 744/629 will be. Imo
Memristors Run AI Tasks at 1/800th Power
These brain-mimicking devices boast tiny energy budgets and hardened circuits
CHARLES Q. CHOI
04 JAN 20234 MIN READ
brain shaped computer wiring against a blue glowing background
ISTOCK
Memristive devices that mimic neuron-connecting synapses could serve as the hardware for neural networks that copy the way the brain learns. Now two new studies may help solve key problems these components face not just with yields and reliability, but with finding applications beyond neural nets.
Memristors, or memory resistors, are essentially switches that can remember which electric state they were toggled to after their power is turned off. Scientists worldwide aim to use memristors and similar components to build electronics that, like neurons, can both compute and store data. These memristive devices may greatly reduce the energy and time lost in conventional microchips shuttling data back and forth between processors and memory. Such brain-inspired neuromorphic hardware may also prove ideal for implementing neural networks—AI systems increasingly finding use in applications such as analyzing medical scans and empowering autonomous vehicles.
However, current memristive devices typically rely on emerging technologies with low production yields and unreliable electronic performance. To help overcome these challenges, researchers in Israel and China fabricated memristive devices using a standard CMOS production line. The resulting silicon synapses the team built boasted a 100 percent yield with 170- to 350-fold greater energy efficiency than a high-performance Nvidia Tesla V100 graphics processing unit when it came to multiply-accumulate operations, the most basic operation in neural networks.
“Memristors are a highly promising lead to provide low-energy-consumption artificial intelligence.”
—Damien Querlioz, Université Paris-Saclay
The scientists developed the new devices using the floating-gate transistor technology used in commercial flash memory. Whereas conventional floating-gate transistors have three terminals, the new components have only two. This greatly simplified fabrication and operation and reduced their size. In addition, memristors have only binary inputs and outputs, eliminating the need for the large, energy-hungry, analog-to-digital and digital-to-analog converters often used in neuromorphic hardware, says study senior author Shahar Kvatinsky, an associate professor of electrical and computer engineering at the Technion-Israel Institute of Technology, in Haifa.
The new devices displayed high endurance, operating past more than 100,000 cycles of programming and erasing by using voltage pulses. In addition, they showed only moderate device-to-device variation and are projected to possess long data retention times of more than 10 years.
The researchers use an array of about 150 of these components to implement a kind of neural network that operated using only binary signals. In experiments, it could recognize handwritten digits with roughly 97 percent accuracy. Kvatinsky says that this work “is just a start—a proof of concept and not a whole integrated chip or a large neural network. Integration and scaling up is a major challenge.”
In another study, a team of French researchers investigated using memristors for the statistical computing technique known as Bayesian reasoning, in which prior knowledge helps compute the chances that an uncertain choice might be correct. Its results are fully explainable—unlike many nearly inscrutable AI computations—and it can perform well when there is little available data, as it can incorporate prior expert knowledge. However, “it is just not obvious how to compute Bayesian reasoning with memristors,” says study coauthor Damien Querlioz, a research scientist at CNRS, Université Paris-Saclay.
Implementing Bayesian reasoning using conventional electronics requires complex memory patterns, “which increase exponentially with the number of observations,” says neuromorphic scientist Melika Payvand at the Institute of Neuroinformatics in Zurich, who did not participate in either study. However, Querlioz and his colleagues “found a way of simplifying this,” she notes.
Memristor AI “excels in safety-critical situations, where high uncertainty is present, little data is available, and explainable decisions are required.”
—Damien Querlioz, Université Paris-Saclay
The scientists rewrote Bayesian equations so a memristor array could perform statistical analyses that harnesses randomness—a.k.a. “stochastic computing.” Using this approach, the array generated streams of semi-random bits at each tick of the clock. These bits were often zeroes but were sometimes ones. The proportion of zeroes to ones encoded the probabilities needed for the statistical calculations the array performed. This digital strategy uses relatively simple circuitry compared to nonstochastic methods, all of which reduces the system’s size and energy demands.
The researchers fabricated a prototype circuit incorporating 2,048 hafnium oxide memristors on top of 30,080 CMOS transistors on the same chip. In experiments, they had the new circuit recognize a person’s handwritten signature from signals beamed from a device worn on the wrist.
Bayesian reasoning is often thought of as computationally expensive with conventional electronics. The new circuit performed handwriting recognition using 1/800th to 1/5,000th the energy of a conventional computer processor, suggesting “that memristors are a highly promising lead to provide low-energy-consumption artificial intelligence,” Querlioz says.
The new device also can instantly flick on and off, suggesting it can work only when needed, to conserve power. Moreover, it is also resilient to errors from random events, making it useful in extreme environments, the researchers say. All in all, the new circuit “excels in safety-critical situations, where high uncertainty is present, little data is available, and explainable decisions are required,” Querlioz says. “Examples are medical sensors or circuits for monitoring the safety of industrial facilities.”
A future direction for the Bayesian circuits might include machines that collect multiple types of sensory data, Payvand says, which might include autonomous vehicles or drones. If the machine is not confident about predictions made based off one sense, it could boost its confidence by analyzing data from a different sense, she notes.
A key obstacle Bayesian systems face “is their scalability to larger problems or networks,” Payvand cautions. Querlioz notes that the team have designed a considerably scaled-up version of their device “that is currently being fabricated.” He notes their circuit is currently specialized for certain types of Bayesian computation, and they want to create more adaptable designs in the future.
To a certain degree, both studies use randomness—Querlioz and his colleagues use it for statistical analysis, while Kvatinsky and his collaborators have their neural networks sample data at random intervals to avoid the kinds of errors that can occur when sampling data a limited number of times.
“These approaches pair very well with the inherited randomness of memristor devices,” says Giacomo Pedretti, a senior AI research scientist at Hewlett Packard Labs, who did not take part in either study. It would be “very interesting” to try to use the inherent noise in these electronics to generate controlled randomness “rather than implementing costly digital pseudorandom number generators,” he says.
Both studies appeared 19 December in the journal Nature Electronics.
This article appears in the March 2023 print issue.
Computer Science | Physics
New memristor design could be a game-changer for AI and big data
by Andrey Feldman | Feb 22, 2024
Computers based on memristors promise significant energy savings and improved accuracy in large-scale computing.
Abstract image of a computer circuit.
Advanced technologies such as neural networks have found extensive application in image recognition, big data processing, financial analysis, and many other fields. However, training them demands significant computational resources and energy consumption, posing challenges for their widespread use and further development.
The problem comes down to bottlenecks imposed by traditional computing systems built using transistors, which keep their memory and processing units separate, requiring power-intensive and performance-degrading data transfers between them. Perhaps an even greater disadvantage is that their memory requires constant power to store information, which further increases energy consumption.
To solve this, researchers propose an alternative: the memristor. “Memristors, also known as memory resistors, are switches that can ‘remember’ their previous electric state, even after power is switched off,” said Desmond Loke, professor at the Singapore University of Technology and Design, in an email.
“Memristors can be used to create devices that store data because they have the ability to drastically reduce the time and energy required for data transmission between memory and processors in traditional microchips,” he continued. “They might be perfect for constructing neural networks, artificial intelligence systems for medical scan processing, and enabling driverless vehicles.”
In a study published in Advanced Physics Research, Loke and his colleagues investigated neural network training using new memristor design that stores information in a unique material made up of germanium, tellurium, and antimony.
This substance exists in an amorphous phase, but when exposed to an electric current and a change in temperature, it exhibits ordered crystalline regions. Depending on the properties of the pulse, such as its intensity and signal shape, the number and size of these regions changes, consequently affecting the material’s electrical and optical properties, which are preserved after the current is turned off. In this way, information can be recorded in the memristor and read from it by repeatedly applying an electric current.
In total, the authors could create fifteen, clearly distinguishable stages of crystallization in the memristor, each corresponding to specific information necessary for training the neural network. “We used [the] memristors to simulate a neural network,” Loke explained. “In trials, the neural network recognized handwritten numerals with an accuracy of over 96%.”
This accuracy is an improvement on other memristor designs by more than 5%, say the team, indicating a promising trajectory for this type of memristor computing technology. But there are still significant hurdles to overcome before this technology can be implemented into real-world computing systems.
“System integration and scale pose considerable challenges,” Loke explained. Nevertheless, the researchers remain hopeful, envisioning a future where memristors might play a pivotal role in training large neural networks. They anticipate smaller, more potent, and dramatically more energy-efficient units compared to conventional computers if the technology can be developed further.
“Currently, this work is just a proof of concept,” Loke concluded. “The next step is to develop a fully integrated circuit and a big neural network.”
Reference: Kian-Guan Lim et al, Toward Memristive Phase-Change Neural Network with High-Quality Ultra-Effective Highly-Self-Adjustable Online Learning, Advanced Physics Research (2024). DOI: 10.1002/apxr.202300085
Feature image credit: AcatXIo on Pixabay
…maybe SBV/V already have it?🤞
Naw. She still has 39 k on the side from scholarships she can use for travel expenses. She got 89,475 of the 94,475 full tuition from institutional grants! Only has to pay 5 k a yr.
great. plane fares could be a budget buster. you might need to move to new haven?
Good question They have sensors on everything else these days. O t. Yale, Duke, Brown all accepted ! Dartmouth waited. Receiving. 89k of the 94 k cost of Yale X 4 years ! The best deal of the 3 🎉🎉🎉🎉😎🤙Go Bulldogs! KAATN’s
why no navigation sensor buoys around the bridge and structures?
inference........like for ai you train it on historical data and synthetic data...like accelerating the training/learning process to provide more potential what ifs'.. when the autonomous vehicles were involved in fatalities, the nvidia chief said they need more training on historical and synthetic data...
perhaps, crazy or more like how they train pilots for the unimaginable line of events. systems failures, even of duplexed systems.?
a reason to have at least 3 rings of power? wags.
Belichick coaching strategy? no such thing as a failsafe? saw the movie freshman year. scarred the you know what out of me.
expect the unpredictable. inference is more about the likelihood of different scenarios.
eg, why did the wh say almost immediately no terrorism in the boat/bridge emergency? boats is headed to sri lanka which is an embattled part of India, the boat has a fire, there is no tug boat accompanying it so close to the bridge. the boat has to signal the bridge of imminent collision? why no radar/proximity alarms? where is the us coast guard? why didn't the harbor pilots immediately call mayday after/if lost power?
who were the workers on the bridge described by country of origin, but not said what nationality was?
my inferometer was going crazy.............you do not rule out terrorism without at least a good look at what the situation is. losing cars and people into the ocean and trying to rescue them is not knowing anything about the situation. coast guard command in the area needs to be examined asap. all ports and international transit points need to be checked. no further souther border transit of illegals to be allowed. if this or other incidents are determined to be terror related, well, the republicans still have majority in congress.
Curt_Hopkins
Memristor tech helps new device store ranges instead of bits and bytes
Curt_Hopkins ?10-05-2021 08:00 AM
layerssized.jpgA group of scientists mostly from Hewlett Packard Labs have published a paper in Nature Communications that outlines a “novel analog content addressable memory (CAM) based on emerging memristor devices for fast look-up table operations.”
Tree-based machine learning performed in-memory with memristive analog CAM was authored by Giacomo Pedretti, Catherine E. Graves, Sergey Serebryakov, Xia Sheng, and Martin Foltin, all of Labs; along with Can Li and Ruibin Mao of the University of Hong Kong; and John Paul Strachan of the Peter Grunberg Insitut.
The accelerator
According to the paper “(t)ree-based machine learning techniques, such as Decision Trees and Random Forests, are top performers in several domains…(h)owever, these models are difficult to optimize for fast inference at scale without accuracy loss in von Neumann architectures due to non-uniform memory access patterns.”
To solve for this problem, lead author Pedretti and the rest of the team “propose for the first time to use the analog CAM as an in-memory computational primitive to accelerate tree-based model inference.” They used an efficient mapping algorithm leveraging the new analog CAM capabilities such that each root-to-leaf path of a Decision Tree is programmed into a row, making this process much faster.
But what the team did exactly was to design a new cell, based on the memristor.
“Thanks to this new device, instead of storing digital information we can store a continuous value,” says Pedretti. “What we store now are ranges and we give an input which is made of continuous values.”
The reason why
“Right now, explainability is the focus of our team,” says Pedretti. “Think of it as a first step towards an ‘accelerator for explainable AI.’”
According to Pedretti, tree-based algorithms are more explainable than neural networks and deep learning. Those working in artificial intelligence have been developing huge, very complex models. But when people have to use the products of those models for industry or government, they often want to know not just what, but why. Why, for example, is a given image classified as a traffic light. Knowing that in situations where proof or law is in question, can be as important as the classification itself.
“Imagine a situation in the financial or insurance industry, where you need to explain why you are not giving money to somebody,” says Pedretti. “Or in a clinical context, you may be required to explain why you gave, or withheld, a drug to a given patient.”
Labs’ CAM-accelerated, tree-based model does not just create desired product, it does so while allowing users to understand how and a specific decision was reached.
An arrival
“The way we designed the stack, from materials to circuit and architecture, based as it is on memristor technology, has allowed us to create an efficient decision-making engine,” says Pedretti. “It has also allowed us to make it in such a way that it is explainable. But in addition to that, it is good.”
What Pedretti means is that they are able to process the data in a massively parallel way, so the accelerator does not have to wait for the first-step decision in the tree to be made before moving on to the rest of the branches. They infer the likely next step, looking at the tree altogether.
The movie “Arrival” and the story it was based on, “The Story of Your Life,” are science fiction. But Fermat’s Theory of Least Time, the mathematical lynchpin of the story, is not. Nor is the idea that you may bring into practice alternate ways of looking at time, life, and certainly computer architecture, ways that do not restrict you to doing one thing as a time.
The Natives are getting restless over at Vcsy-chat site. We’re all tired. Worn out really. Pissed off to put it mildly. But what can we do other than trust in our BoD at this point? Pretty much, nothing. I want to believe Len and his men have a plan. I think everyone needs to relax. Take a chill pill and go to the beach or forest or desert or whatever relaxes you. Not much longer and we’ll all hear some thing. .
And Yes. I think Milks should be sued for whatever we can sue him for and make him suffer the penalties. All in due time.
I read the article. It’s a good thing our Markman Hearing was over with years ago now. It seems the Chinese are pulling out all the stops. SBV/V should be careful. What’s next?
journal ed page.....ceo of tech company responds to intel accusations of security risk due to foreign investors.
might not trade as a jv of v ip and other techs?
You bought into this scam while some of the actors here pumped it years ago, and it's still a scam. This "stock" will never trade again imo. The new "management" is just a bunch of vultures who will suck every last penny they can out of this worthless company. The only thing left is failing Now Solutions and a bunch of worthless patents. Most of the patents have expired.
today news/pr.....adobe cloud experience integrated with msft dynamics 365.... some emPath?
remember when the former msft ceo went to talk to the adobe people...before he left to do b ball?
cpaas between the application and cloud ai? ploinks and puddle? wags.
today news/pr.....adobe cloud experience integrated with msft dynamics 365.... some emPath?
remember when the former msft ceo went to talk to the adobe people...before he left to do b ball?
cpaas between the application and cloud ai? ploinks and puddle? wags.
v ip secure place for token: i'm thinking, sk hynix and indiana plant to be. sk hynix and hp memristor memory ? how to maintain a more secure password/token ip? use electromagnetic state and 3d architecture?
old databases need to be optimized for ai/generative ai.....historical/synthetic//realtime...guesses.
Vertica is a columnar database management software designed for analyzing large volumes of structured data efficiently using SQL. It offers a robust set of SQL elements, data types, functions, and statements to manage and analyze massive amounts of data quickly and reliably. While Vertica excels in handling structured data through its column-store architecture, it also supports semi-structured and unstructured data storage, providing users with a versatile platform for various data analysis needs. Additionally, Vertica is known for its high-speed business intelligence capabilities, advanced analytics features, and support for machine learning algorithms integrated into the SQL or Python environment. The software is horizontally scalable and can be deployed on-premises or in the cloud across major cloud platforms like Amazon AWS, Microsoft Azure, and Google Cloud Platform. Vertica's strengths lie in its ability to process large volumes of data efficiently, making it a valuable tool for organizations seeking powerful analytics solutions for their structured and semi-structured data sets
Vertical Computer Systems Inc. (VCSY) is an international provider of application software, cloud-based services, Internet core technologies, and intellectual property assets. VCSY markets administrative software products and is developing various products to enhance its offerings. On the other hand, Vertica is an analytic database management software company that offers a robust set of SQL elements for managing and analyzing massive volumes of data efficiently. While VCSY focuses on software services and core technologies, Vertica specializes in providing advanced analytics solutions through its database management software
"Microsoft is utilizing SONiC (Software for Open Networking in the Cloud) to power its global cloud network infrastructure. By leveraging SONiC, Microsoft can deploy new features seamlessly without disrupting end users, roll out updates securely and reliably across its network fleet in a matter of hours, and utilize cloud-scale deep telemetry for automated failure mitigation. SONiC enables Microsoft to control all hardware elements in the network using a unified Software-Defined Networking software, ensuring efficient network operations and management. Microsoft has open-sourced SONiC to the community, making it available on their GitHub repository, fostering a large ecosystem of hardware and software partners that offer various switching platforms and components. This approach allows operators to benefit from rapid innovation in hardware while maintaining a unified software solution across multiple platforms, enhancing scalability and flexibility in network operations" says perplexity ai.
write it once and then send to distribution which changes it for the platform, os, etc of the native device to function as desired? sqlize it... and allow executables. mosf defn 744. wags.
not according to wells fargo. they don't know how to value vcsy. so they say.
value equals zero. Cost basis is the loss
and yet it still cannot be written off cuz the brokers don't know how to value it.
I have completely written this off. I see the probability of this ever trading again or being worth anything as infinitesimally small. It's been 1,245 days since the management change and the forward movement has been at a snail's pace. Something like the half-life of Uranium
thin client control of mainframe...and neoware
valde and laptop/pc control of mainframe.
now ? server to server control/api's and something like x87?
8x8 and 8 work over the top of embedded os. guesses. not two os'es on same device. one on top of the embedded os? just need software. like jitsi as a service. guesses. and this could be the secret of SONiC networking. It's just software and it helps define the network fabric? if true/so, a reason for a big share price move.
sonic networking.......linux opensource.....neoware was using linux with rhat ....neolinux eon anthing. however, the tried and failed with eon switches....as i remember. maybe a reason besides the vcsy patent for 744?
but now msft and SONiC networking where software works on all the hardware.. why cuz it's over the top? or embedded? i don't know.
but anyway broadcom and sonic
thinking cisco effected by such...therefore , laid off networking types. why? maybe 8 automatic networking, and dynamic routing and authentication now makes linux work for switches...softswitches of 8 in particular?
the 8 management board had a member resign suddenly due to no malice of either parties . safeguard scientifics.......they will say they don't know but........
what else is that company invested in? something to profit from being able to provide the linux open source switching. ?
wikipedia:
The Software for Open Networking in the Cloud or alternatively abbreviated and stylized as SONiC, is a free and open source network operating system based on Linux. It was originally developed by Microsoft and the Open Compute Project. In 2022, Microsoft ceded oversight of the project to the Linux Foundation, who will continue to work with the Open Compute Project for continued ecosystem and developer growth.[1][2][3][4] SONiC includes the networking software components necessary for a fully functional L3 device[5] and was designed to meet the requirements of a cloud data center. It allows cloud operators to share the same software stack across hardware from different switch vendors and works on over 100 different platforms.[3][5][6] There are multiple companies offering enterprise service and support for SONiC.
Overview
SONiC was developed and open sourced by Microsoft in 2016.[2] The software decouples network software from the underlying hardware and is built on the Switch Abstraction Interface API.[1] It runs on network switches and ASICs from multiple vendors.[2] Notable supported network features include Border Gateway Protocol (BGP), remote direct memory access (RDMA), QoS, and various other Ethernet/IP technologies.[2] Much of the protocol support is provided through inclusion of the FRRouting suite of routing daemons.[7]
The SONiC community includes cloud providers, service providers, and silicon and component suppliers, as well as networking hardware OEMs and ODMs. It has more than 850 members.[2]
The source code is licensed under a mix of open source licenses including the GNU General Public License and the Apache License, and is available on GitHub.[8][9]
SONiC networking came from msft work and opensource.........ain't that a .......
8x8 and softswitch ip
but v ip for abstraction of the maker of the switch from it's functionality?
msft and 744 on display...and to me opensource doesn't protect where it came from because v to our knowledge never game up any of their ip/patents to opensource.
THUMP! ( sound of my forehead hitting my desk)
any chance v ip money in the budget now being done?
Followers
|
52
|
Posters
|
|
Posts (Today)
|
12
|
Posts (Total)
|
12115
|
Created
|
11/14/02
|
Type
|
Free
|
Moderators |
Volume | |
Day Range: | |
Bid Price | |
Ask Price | |
Last Trade Time: |