Home / Technology / AI & IT / Memcomputing to accelerate deep learning and Space-based Intelligence, Surveillance, and Reconnaissance

Memcomputing to accelerate deep learning and Space-based Intelligence, Surveillance, and Reconnaissance

By 2020, there are expected to be more than 200 billion interconnected devices within the Internet of Things framework – these will generate an incredible amount of data that will need processing. Traditionally, the processing of data in electronics has relied on integrated circuits (chips) featuring vast numbers of transistors – microscopic switches that control the flow of electrical current by turning it on or off. The size of transistors has reduced to meet the increasing demands of technology, but are now reaching their physical limit, with – for example – the processing chips that power smartphones containing an average of five billion transistors.


Computers require costly, constant and slow communications between their processor and memory to retrieve large amounts data. This makes them large, expensive and power-hungry. The so-called von Neumann Bottleneck in today’s computing is created precisely from the physical separation of the CPU and the memory unit: the CPU has to constantly insert and extract information from the memory, significantly slowing processing time.


Researchers are now developing new architectures to speed up the processing. One anticipated capability is quantum computing—technology that follows the laws of quantum physics, enabling processing power to exist in multiple states and perform multiple tasks at the same time.


Memcomputing is a novel computing paradigm  that employs memory (time non-locality) to both store and process information on the same physical location. Memory may be due to any physical property of the system, whether spin, charge or atomic configuration. Digital, hence scalable, memcomputing machines can be designed to solve complex problems very efficiently both in hardware and in software.


Di Ventra explained that memcomputing accelerates the time to find feasible solutions to the most complex optimization problems in all industries. “Using a physics-based approach, this novel computing paradigm employs memory to both process and store information on the same physical location, a property that somewhat mimics the computational principles of the human brain,” said the UC San Diego physics professor and author of “The Scientific Method: Reflections from a Practitioner (Oxford University Press, 2018).”


The inspiration for memcomputing came to Di Ventra when he learned that even simple organisms, such as amoebas, can “learn” patterns when appropriately trained, and realized that such a behavior is a consequence of the ability of the organism to store that information in some form of physical memory, and retrieve it for later use to perform simple tasks. Following up on this work, Di Ventra and his team then started to investigate whether such a behavior could also be used to compute some problems, such as finding the solution of a maze, the shortest path in networks, and some optimization problems. The success of these early studies gave more support to the notion that memory can indeed be used as an efficient computational tool in novel architectures without the need to physically separate the CPU from the memory bank as it is currently done in our modern computers. This type of computing instead resembles closer the one that is believed to occur in the brain.


After years of trial and error, Di Ventra and his group developed all of the mathematics required for this new simple architecture, combining “memory” and “compute” and driven by a specialized “computational memory” unit, with performance that resembles quantum computing—without the overwhelming computational overhead.


Unlike quantum computing, memcomputing employs non-quantum units so it can be realized in hardware with available technology and emulated in software on traditional computers


“We have applied these emulations to a wide variety of difficult computational problems that are of interest to both academia and industry, and solved them orders of magnitude faster than traditional algorithms,” noted Di Ventra.


MemComputing, Inc.’s disruptive technology is accelerating the time to find feasible solutions to challenging operations research problems. Using physics principles, MemComputing’s novel software architecture is based on the logic and reasoning functions of the human brain. The company was formed by the inventors of the memcomputing architecture, Dr. Massimiliano Di Ventra and Dr. Fabio Traversa, with John A. Beane, former Entrepreneur-in-Residence, University of California, San Diego.


“Memcomputing represents a radical departure from both our traditional computers, and algorithms that run on them, and quantum computers,” said Di Ventra. “It provides the necessary tools for the realization of an adaptable computational platform deployable in the field of artificial intelligence and offers strategic advantages to the Department of Defense in numerous applications,” said Di Ventra.


DARPA funds memcomputing for AI

MemComputing’s co-founder, Max Di Ventra, has been granted half-a-million dollars over 18 months from the Defense Advanced Research Projects Agency (DARPA) to further develop MemComputing’s technology and its applications to AI.


“Our project, if successful, would have a large impact in the field of machine learning and artificial intelligence by showing that physics approaches can be of great help in fields of research that are traditionally dominated by computer scientists,” said Di Ventra.


With the DARPA funds, the team will apply memcomputing to the unsupervised learning, or pre-training, of Deep Belief Networks. These are systems of multi-layer neural networks (NNs) used to recognize, generate and group data. DiVentra will also propose a hardware architecture, using current technologies, to perform this task. Pre-training of NNs is a notoriously difficult problem, and researchers have all but abandoned it in favor of supervised learning. However, in order to have machines that adapt to external stimuli in real time and make decisions according to the context in which they operate—the goal of the third wave of AI—powerful new methods to train NNs in an unsupervised manner are required.


MemComputing Selected to Join Air Force Research Laboratory’s Catalyst Space Accelerator

MemComputing, Inc., developer of disruptive high performance computing technology, today announced it has been selected as one of eight startups nationwide to join the Catalyst Space Accelerator, centered around space-based Intelligence, Surveillance, and Reconnaissance (ISR).


The Catalyst Space Accelerator is sponsored by the Air Force Research Laboratory (AFRL) Space Vehicles Directorate, a defense and national security industry accelerator headquartered on the Catalyst Campus in Colorado Springs, Colorado.


“The Accelerator provides MemComputing the opportunity to work with government and commercial leaders with access to an extensive collaborative ecosystem,” said John Beane, CEO of MemComputing, Inc. “The type of complex computations faced by space-based Intelligence, Surveillance, and Reconnaissance programs are perfectly suited to benefit by the acceleration that our MemCPU™ technology provides. Compute problems taking hours, days, and weeks are reduced to minutes and seconds using MemComputing.”



References and Resources also include:





About Rajesh Uppal

Check Also

DARPA’s ANSR Program: Transforming AI for Military Autonomy with Trustworthy Hybrid Methods

Introduction: Artificial Intelligence (AI) has evolved rapidly, propelling machines to match or surpass human intelligence …

error: Content is protected !!