Researchers have created spiking neural nets with thousands of memristors (that mimic how neurons operate) by using atomically thin layer of material. Spiking neural networks should be better than regular neural networks where there is the need for intelligence to react to real-time inputs. Regular neural networks are better for more static information. Exploiting the …
New materials may also enable entirely new paradigms for individual chip components and their overall design. One long-promised advance is the ferroelectric field-effect transistor, or FE-FET. Such devices could switch states rapidly enough to perform computation, but also be able to hold those states without being powered, enabling them to function as long-term memory storage. …
There was a lot of hype and promise around memristors and HPE bet huge amounts of research around creating a new computer paradigm around memristors and memory driven computing. The last major flurry of information and presentations from HPE was in 2018. From 2014-2018, HPE launched memory driven computing that was supposed to leverage memristor …
1. A memristor has been proposed as an artificial synapse for emerging neuromorphic computing applications. (Nature Nanotechnology) To train a neural network in memristor arrays, changes in weight values in the form of device conductance should be distinct and uniform. An electrochemical metallization (ECM) memory typically based on silicon (Si), has demonstrated a good analogue …
University of Massachusetts researchers have successfully made a 2 nanometer individually addressable memristors. It is capable of being mass-produced in conventional fabs. This could be great for neuromorphic computing and AI in general. This should lead to high-density memristor arrays with low power consumption for both memory and unconventional computing applications. There were difficulties in …
Up until now small variations in the current passing through a memristor device was not precise enough for numerical calculations. The Nanoelectronics group, University of Michigan, got around this problem by digitizing the current outputs—defining current ranges as specific bit values (i.e., 0 or 1). The team was also able to map large mathematical problems …
Scientists at the National Institute of Standards and Technology (NIST) have now unveiled the long-mysterious inner workings of these semiconductor elements, which can act like the short-term memory of nerve cells. Just as the ability of one nerve cell to signal another depends on how often the cells have communicated in the recent past, the …
University of Michigan researchers created a reservoir computing system that reduces training time and improves capacity of similar neural networks. A new type of neural network made with memristors can dramatically improve the efficiency of teaching machines to think like humans. The network, called a reservoir computing system, could predict words before they are said …
Dubai has tested a Chinese prototype of a self-driving hover-taxi, its transport authority said on Monday, with the aim of introducing the aerial vehicle in the emirate by July. The test of the one-man electric vehicle comes as the city state in the United Arab Emirates seeks to ensure a quarter of its means of …
The Marine Corps is investigating after an F-35B Joint Strike Fighter based out of Beaufort, South Carolina, recently caught fire in mid-air, Military.com has learned. The incident happened Oct. 27 at Marine Fighter Attack Training Squadron 501, a fleet replacement squadron for the Marine Corps consisting of 20 F-35B aircraft. One of the aircraft experienced …
University of Alabama at Birmingham researchers will use pressures greater than those found at the center of the Earth to potentially create as yet unknown new materials. In the natural world, such immense forces deep underground can turn carbon into diamonds, or volcanic ash into slate. The ability to produce these pressures depends on tiny …