TY - JOUR
T1 - Low-Power Neuromorphic Hardware for Signal Processing Applications
T2 - A review of architectural and system-level design approaches
AU - Rajendran, Bipin
AU - Sebastian, Abu
AU - Schmuker, Michael
AU - Srinivasa, Narayan
AU - Eleftheriou, Evangelos
N1 - Funding Information:
Bipin Rajendran received partial support for this work from the U.S. National Science Foundation grant 1710009 and
Funding Information:
Michael Schmuker (m.schmuker@herts.ac.uk) received his M.Sc./diploma degree in biology from Albert Ludwigs University, Freiburg, Germany, in 2003 and his Ph.D. degree in chemistry from Goethe University Frankfurt am Main, Germany, in 2007. He has postdoctoral experience in computational neuroscience and neuromorphic computing and is currently a reader in data science in the Department of Computer Science, University of Hertfordshire, Hatfield, United Kingdom. His research translates neurobiological principles of sensory computing into algorithms for data processing, inference, and control, with a focus on neuromor-phic olfaction and gas-based navigation. In 2014, he joined the University of Sussex, Falmer, United Kingdom, on a Marie Curie Fellowship (European Commission). In 2016, he joined the University of Hertfordshire.
Funding Information:
Abu Sebastian (ZRLASE@ch.ibm.com) received his B. E. (honors) degree in electrical and electronics engineering from the Birla Institute of Technology and Science, Pilani, India, in 1998 and his M.S. and Ph.D. degrees in electrical engineering from Iowa State University, Ames, in 1999 and 2004, respectively. He is a principal research staff member and master inventor at IBM Research Zürich. He was a contributor to several key projects in the area of storage and memory technologies and currently leads the research effort on in-memory computing at IBM Research Zürich. He is a corecipient of the 2009 IEEE Control Systems Technology Award and the 2009 IEEE Transactions on Control Systems Technology Outstanding Paper Award. In 2015, he received a European Research Council Consolidator Grant.
Funding Information:
grant 2717.001 from the Semiconductor Research Corporation. Michael Schmuker received funding from the European Com- mission (H2020, Human Brain Project), grant 785907. Abu Sebastian acknowledg-es support from the European Research Council through the European Union’s Horizon 2020 Research and Innovation Program under grant 682675.
Publisher Copyright:
© 1991-2012 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Machine learning has emerged as the dominant tool for implementing complex cognitive tasks that require supervised, unsupervised, and reinforcement learning. While the resulting machines have demonstrated in some cases even superhuman performance, their energy consumption has often proved to be prohibitive in the absence of costly supercomputers. Most state-of-the-art machine-learning solutions are based on memoryless models of neurons. This is unlike the neurons in the human brain that encode and process information using temporal information in spike events. The different computing principles underlying biological neurons and how they combine together to efficiently process information is believed to be a key factor behind their superior efficiency compared to current machine-learning systems.
AB - Machine learning has emerged as the dominant tool for implementing complex cognitive tasks that require supervised, unsupervised, and reinforcement learning. While the resulting machines have demonstrated in some cases even superhuman performance, their energy consumption has often proved to be prohibitive in the absence of costly supercomputers. Most state-of-the-art machine-learning solutions are based on memoryless models of neurons. This is unlike the neurons in the human brain that encode and process information using temporal information in spike events. The different computing principles underlying biological neurons and how they combine together to efficiently process information is believed to be a key factor behind their superior efficiency compared to current machine-learning systems.
UR - http://www.scopus.com/inward/record.url?scp=85074460168&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074460168&partnerID=8YFLogxK
U2 - 10.1109/MSP.2019.2933719
DO - 10.1109/MSP.2019.2933719
M3 - Article
AN - SCOPUS:85074460168
SN - 1053-5888
VL - 36
SP - 97
EP - 110
JO - IEEE Signal Processing Magazine
JF - IEEE Signal Processing Magazine
IS - 6
M1 - 8888024
ER -