We have heard about a great number of new architectures and approaches to scalable and efficient deep learning processing that sit outside of the standard CPU, GPU, and FPGA box and while each is different, many are leveraging a common element at all-important memory layer.
CS Digest Section: Neuromorphic Computing
The National Science Foundation (NSF) has awarded 18 grants to multidisciplinary teams from across the United States to conduct frontier research focused on neural and cognitive systems. Each award provides a research team with up to $1 million over two to four years.
Brain2Grid SCADA system being "grown" by Clemson and Georgia Tech -"Neurocontrol offers nonlinear adaptive optimal control"
$110M effort by NIH, NSF and DARPA in 2014 for a "new generation of information processing systems"
Chip-architecture breakthrough accelerates path to exascale computing; Helps computers tackle complex, cognitive tasks such as pattern recognition and sensory processing.
Brain Computer Interface (BCI) research promises to be a billion dollar a year enterprise, with broad application.
U. of W demonstrates remote control of another human body via Brain Computer Interface breakthrough
An influential group of European neuroscientists is threatening to boycott the Human Brain Project (HBP), the hugely ambitious plan to map the entire human brain in computer models that is slated to receive up to 1 billion Euros in funding from the European Union and its member countries.
Researchers have built and demonstrated a novel configurable computing device that uses a thousand times less electrical power – and can be built up to a hundred times smaller – than comparable digital floating-gate configurable devices currently in use.
Google has developed a deep-learning neural network program that beats well-traveled humans at guessing where a photo was taken.