While computers have become smaller and more powerful and supercomputers and parallel computing have become the standard, we are about to hit a wall in energy and miniaturization. Now, Penn State researchers have designed a 2D device that can provide more than yes-or-no answers and could be more brainlike than current computing architectures.
“Complexity scaling is also in decline owing to the non-scalability of traditional von Neumann computing architecture and the impending ‘Dark Silicon’ era that presents a severe threat to multi-core processor technology,” the researchers note in today’s (Sept 13) online issue of Nature Communications.
The Dark Silicon era is already upon us to some extent and refers to the inability of all or most of the devices on a computer chip to be powered up at once. This happens because of too much heat generated from a single device. Von Neumann architecture is the standard structure of most modern computers and relies on a digital approach — “yes” or “no” answers — where program instruction and data are stored in the same memory and share the same communications channel.
“Because of this, data operations and instruction acquisition cannot be done at the same time,” said Saptarshi Das, assistant professor of engineering science and mechanics. “For complex decision-making using neural networks, you might need a cluster of supercomputers trying to use parallel processors at the same time — a million laptops in parallel — that would take up a football field. Portable healthcare devices, for example, can’t work that way.”
The solution, according to Das, is to create brain-inspired, analog, statistical neural networks that do not rely on devices that are simply on or off, but provide a range of probabilistic responses that are then compared with the learned database in the machine. To do this, the researchers developed a Gaussian field-effect transistor that is made of 2D materials — molybdenum disulfide and black phosphorus. These devices are more energy efficient and produce less heat, which makes them ideal for scaling up systems.
“The human brain operates seamlessly on 20 watts of power,” said Das. “It is more energy efficient, containing 100 billion neurons, and it doesn’t use von Neumann architecture.”
The researchers note that it isn’t just energy and heat that have become problems, but that it is becoming difficult to fit more in smaller spaces.
“Size scaling has stopped,” said Das. “We can only fit approximately 1 billion transistors on a chip. We need more complexity like the brain.”
The idea of probabilistic neural networks has been around since the 1980s, but it needed specific devices for implementation.
“Similar to the working of a human brain, key features are extracted from a set of training samples to help the neural network learn,” said Amritanand Sebastian, graduate student in engineering science and mechanics.
The researchers tested their neural network on human electroencephalographs, graphical representation of brain waves. After feeding the network with many examples of EEGs, the network could then take a new EEG signal and analyze it and determine if the subject was sleeping.
“We don’t need as extensive a training period or base of information for a probabilistic neural network as we need for an artificial neural network,” said Das.
The researchers see statistical neural network computing having applications in medicine, because diagnostic decisions are not always 100% yes or no. They also realize that for the best impact, medical diagnostic devices need to be small, portable and use minimal energy.
Das and colleagues call their device a Gaussian synapse and it is based on a two-transistor setup where the molybdenum disulfide is an electron conductor, while the black phosphorus conducts through missing electrons, or holes. The device is essentially two variable resistors in series and the combination produces a graph with two tails, which matches a Gaussian function.
The Latest on: Probabilistic computing
via Google News
The Latest on: Probabilistic computing
- Europe’s two peace missionson December 4, 2021 at 1:04 pm
On both climate change and new dual-use technologies, Europe’s foundational peace project should become global. The region’s devastation in two world wars has stripped it of the desire to dominate ...
- Department of Computing PhD Winter Conferenceon December 3, 2021 at 8:00 am
Prior to entering industry, Zehan completed a PhD in medical image analysis as well as a masters in joint mathematics and computer science from Imperial College London. In his spare time, Zehan is ...
- Twin Futures And 'A New Space Race'on December 1, 2021 at 10:25 am
For two hundred years, probability theory has offered statistical forecasts – estimates on everything from expected return on investments to expected goals from football teams.
- Machine Learning Reduces Uncertainty in Breast Cancer Diagnoseson November 30, 2021 at 9:00 pm
Researchers at Michigan Tech have developed a machine learning model for detecting breast cancer from histopathology images — tissues and cells examined under microscope. The model can classify benign ...
- Bristol’s Smart Internet Lab aims to deliver ‘quantum data center of the future’on November 30, 2021 at 2:11 pm
Smart Internet Lab is to work with industry partners to develop the first blueprint for a quantum data center, as part of UKRI’s £170 million. Launched in April 2018, UKRI is a non-departmental public ...
- Kaggle Competition | Porto Seguro’s Safe Driver Predictionon November 29, 2021 at 10:05 am
Insurance Claim Prediction. Contribute to arjhuang/kaggle-porto-seguro development by creating an account on GitHub.
- After Rising 18% Over The Last Month, What’s Next For Snowflake Stock?on November 29, 2021 at 7:45 am
Snowflake stock has declined by about 11% over the last week (five trading days), underperforming the broader S&P 500 which remained roughly flat over the same period. The decline is likely driven by ...
- JASMINER X4 became the first Ethereum mining chipon November 29, 2021 at 4:42 am
JASMINER released the first Ethereum mining chip-Jasminer X4. For those who still blindly pursue mining machines with high computing ...
- Break up Amazon? Our survey suggests it may not be necessaryon November 27, 2021 at 11:40 am
Amazon faces many disruption challenges, independent of any government intervention. Specifically, respondents to our survey believe that history will repeat itself in that there’s a 60% probability ...
- Interviewing the World's Most Complex AI on the Metaverseon November 23, 2021 at 1:28 pm
OpenAI's Generative Pre-trained Transformer 3 (GPT-3) is the worlds most complex language model that just became available to the general public. The first and most important thing to understand is th ...
via Bing News