Persuading Computers to Act More Like Brains

Ames, Heather; Versace, Massimiliano; Gorchetchnikov, Anatoli; Chandler, Benjamin; Livitz, Gennady; Léveillé, Jasmin; Mingolla, Ennio; Carter, Dick; Abdalla, Hisham; Snider, Greg

doi:10.1007/978-94-007-4491-2_4

Cited by 5 publications

(2 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of the common applications of neuromorphic systems for robotics include learning a particular behavior [2548], [2549], locomotion control or control of particular joints to achieve a certain motion [67]- [69], [361], [663], [1082], [1083], [1261], [1279], [1527], [1784], [1885], [2550], [2551], social learning [2552], [2553], and target or wall following [498], [606], [1576], [1682], [2554]. Thus far, in terms of robotics, the most common use of neuromorphic implementations is for autonomous navigation tasks [16], [195], [393], [486], [532], [547], [735], [1077], [1329]- [1333], [1339], [1503], [1539], [1563], [1671], [1716], [2379], [2555]- [2560]. In the same application space as robotics is the generation of motion through central pattern generators (CPGs).…”

Section: Applicationsmentioning

confidence: 99%

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

176

180

View full text Add to dashboard Cite

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture. This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems. The promise of the technology is to create a brainlike ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities. In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history. We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications. We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled. The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed.

show abstract

Section: Applicationsmentioning

confidence: 99%

A Survey of Neuromorphic Computing and Neural Networks in Hardware

Schuman¹,

Potok²,

Patton³

et al. 2017

Preprint

176

180

View full text Add to dashboard Cite

show abstract

“…Compared with the human brain, current AI technologies cannot perform efficient processing and they consume significant power. For example, AlphaGo, which has defeated a number of professional Go players, consumes 250 kW, whereas the human brain consumes only 20 W . Enormous power consumption is a serious limitation for AI data processing; thus, for practical application of AI, not only software but also hardware that enables more efficient processing needs to be developed.…”

Section: Introductionmentioning

confidence: 99%

Crystalline IGZO ceramics (crystalline oxide semiconductor)–based devices for artificial intelligence

Yamazaki

Ohshita

Oota

et al. 2019

Int J Ceramic Engine & Sci

View full text Add to dashboard Cite

In 2009, a crystalline oxide semiconductor with a layered structure, which we refer to as c‐axis–aligned crystalline indium‐gallium‐zinc oxide (CAAC‐IGZO), was first discovered. CAAC‐IGZO has a peculiar crystal structure in which clear grain boundaries are not observed despite high c‐axis alignment and absence of a‐b plane alignment. When compared to a Si field‐effect transistor (FET), a metal‐oxide‐semiconductor (MOS) FET, utilizing CAAC‐IGZO, presents lower off‐state current (on the order of yA [10−24 A]). These unique characteristics allow CAAC‐IGZO to realize devices with low power consumption. With the emerging era of artificial intelligence, wherein power saving becomes more significant, CAAC‐IGZO has attracted attention as a potential replacement for Si. This paper describes the characteristics and potentials of CAAC‐IGZO for the development of memory devices with unprecedented functions.

show abstract