Toggle light / dark theme

Engineers put tens of thousands of artificial brain synapses on a single chip

MIT engineers have designed a “brain-on-a-chip,” smaller than a piece of confetti, that is made from tens of thousands of artificial brain synapses known as memristors—silicon-based components that mimic the information-transmitting synapses in the human brain.

The researchers borrowed from principles of metallurgy to fabricate each memristor from alloys of silver and copper, along with silicon. When they ran the chip through several , the chip was able to “remember” stored images and reproduce them many times over, in versions that were crisper and cleaner compared with existing memristor designs made with unalloyed elements.

Their results, published today in the journal Nature Nanotechnology, demonstrate a promising new memristor design for neuromorphic devices—electronics that are based on a new type of circuit that processes information in a way that mimics the brain’s neural architecture. Such brain-inspired circuits could be built into small, , and would carry out complex computational tasks that only today’s supercomputers can handle.

This wearable robotic arm can hold tools, pick fruit, and punch through walls

We’ve always had a soft spot for supernumerary robotic limbs here at The Verge, but this latest example of the genre is one of the most impressive we’ve seen to date. Designed by researchers at the Université de Sherbrooke in Canada, it’s a hydraulic arm that sits on the wearer’s hip and uses a three-fingered manipulator to carry out a range of tasks.

MIT fit tens of thousands of artificial brain synapses on a single chip

Someday, we might be able to carry around tiny, AI brains that can function without supercomputers, the internet or the cloud. Researchers from MIT say their new “brain-on-a-chip” design gets us one step closer to that future. A group of engineers put tens of thousands of artificial brain synapses, known as memristors, on a single chip that’s smaller than a piece of confetti.

In a paper published in Nature Nanotechnology, the researchers explain how their brain-inspired chip was able to remember and recreate a gray-scale image of Captain America’s shield and reliably alter an image of MIT’s Killian Court by sharpening and blurring it. Those tests may seem minor, but the team believes the chip design could advance the development of small, portable AI devices and carry out complex computational tasks that today only supercomputers are capable of.

“So far, artificial synapse networks exist as software. We’re trying to build real neural network hardware for portable artificial intelligence systems,” says Jeehwan Kim, associate professor of mechanical engineering at MIT. “Imagine connecting a neuromorphic device to a camera on your car, and having it recognize lights and objects and make a decision immediately, without having to connect to the internet.”

Robots with flexible feet walk 40% faster

Researchers from the University of California San Diego (UCSD) have developed flexible feet that can help robots walk up to 40% faster on uneven terrain such as pebbles and wood chips. The work has applications for search-and-rescue missions, as well as space exploration.

“Robots need to be able to walk fast and efficiently on natural, uneven terrain, so they can go everywhere humans can, but maybe shouldn’t,” said Emily Lathrop, the study’s first author and a PhD student in the Jacobs School of Engineering at UCSD.

The researchers are presenting their breakthrough at the RoboSoft conference, taking place virtually from now until 15th July.

AI Transforming The Construction Industry

Construction is one of the oldest professions as people have been building shelters and structures for millennia. However the industry has evolved quite a bit in the way they design, plan, and build structures. For decades, technology has been used in the construction industry to make jobs more efficient and construction projects and structures safer.

In recent years, construction companies have increasingly started using AI in a range of ways to make construction more efficient and innovative. From optimizing work schedules to improving workplace safety to keeping a secure watch on construction facilities, https://www.cognilytica.com/2019/06/26/ai-today-podcast-95-a…struction/ href=https://www.cognilytica.com/2019/06/26/ai-today-podcast-95-ai-use-case-series-ai-in-construction/ rel=“nofollow noopener noreferrer” target=_blank title=https://www.cognilytica.com/2019/06/26/ai-today-podcast-95-ai-use-case-series-ai-in-construction/>AI in the construction industry is already proving its value.

OpenAI & UberAI Proposed A New Method To Neural Architecture Search

Recently, OpenAI collaborated with UberAI to propose a new approach — Synthetic Petri Dish — for accelerating the most expensive step of Neural Architecture Search (NAS). The researchers explored whether the computational efficiency of NAS can be improved by creating a new kind of surrogate, one that can benefit from miniaturised training and still generalise beyond the observed distribution of ground-truth evaluations.

Deep neural networks have been witnessing success and are able to mitigate various business challenges such as speech recognition, image recognition, machine translation, among others for a few years now.

According to the researchers, Neural Architecture Search (NAS) explores a large space of architectural motifs and is a compute-intensive process that often involves ground-truth evaluation of each motif by instantiating it within a large network, and training and evaluating the network with thousands or more data samples. By motif, the researchers meant the design of a repeating recurrent cell or activation function that is repeated often in a larger Neural Network blueprint.

Artificial brains may need sleep too

No one can say whether androids will dream of electric sheep, but they will almost certainly need periods of rest that offer benefits similar to those that sleep provides to living brains, according to new research from Los Alamos National Laboratory.

“We study spiking , which are systems that learn much as living brains do,” said Los Alamos National Laboratory computer scientist Yijing Watkins. “We were fascinated by the prospect of training a neuromorphic processor in a manner analogous to how humans and other biological systems learn from their environment during childhood development.”

Watkins and her research team found that the simulations became unstable after continuous periods of unsupervised learning. When they exposed the networks to states that are analogous to the waves that living brains experience during sleep, stability was restored. “It was as though we were giving the neural networks the equivalent of a good night’s rest,” said Watkins.