B
Blake A. Richards
Researcher at McGill University
Publications - 100
Citations - 4750
Blake A. Richards is an academic researcher from McGill University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 23, co-authored 74 publications receiving 3168 citations. Previous affiliations of Blake A. Richards include Canadian Institute for Advanced Research & Centre for Addiction and Mental Health.
Papers
More filters
Journal ArticleDOI
A deep learning framework for neuroscience
Blake A. Richards,Timothy P. Lillicrap,Philippe Beaudoin,Yoshua Bengio,Yoshua Bengio,Rafal Bogacz,Amelia J. Christensen,Claudia Clopath,Rui Ponte Costa,Rui Ponte Costa,Archy O. de Berker,Surya Ganguli,Surya Ganguli,Colleen J Gillon,Danijar Hafner,Danijar Hafner,Adam Kepecs,Nikolaus Kriegeskorte,Peter E. Latham,Grace W. Lindsay,Kenneth D. Miller,Richard Naud,Christopher C. Pack,Panayiota Poirazi,Pieter R. Roelfsema,João Sacramento,Andrew M. Saxe,Benjamin Scellier,Anna C. Schapiro,Walter Senn,Greg Wayne,Daniel L. K. Yamins,Friedemann Zenke,Friedemann Zenke,Joel Zylberberg,Joel Zylberberg,Denis Therien,Konrad P. Kording,Konrad P. Kording +38 more
TL;DR: It is argued that a deep network is best understood in terms of components used to design it—objective functions, architecture and learning rules—rather than unit-by-unit computation.
Journal ArticleDOI
Hippocampal neurogenesis regulates forgetting during adulthood and infancy.
Katherine G. Akers,Alonso Martinez-Canabal,Leonardo Restivo,Adelaide P. Yiu,Antonietta De Cristofaro,Hwa-Lin Liz Hsiang,Anne L. Wheeler,Axel Guskjolen,Yosuke Niibori,Hirotaka Shoji,Koji Ohira,Blake A. Richards,Tsuyoshi Miyakawa,Sheena A. Josselyn,Paul W. Frankland +14 more
TL;DR: Throughout life, new neurons are continuously added to the dentate gyrus, and as this continuous addition remodels hippocampal circuits, computational models predict that neurogenesis leads to degradation or forgetting of established memories.
Journal ArticleDOI
Neurons are recruited to a memory trace based on relative neuronal excitability immediately before training
Adelaide P. Yiu,Valentina Mercaldo,Chen Yan,Blake A. Richards,Asim J. Rashid,Hwa-Lin Liz Hsiang,Jessica C. Pressey,Vivek Mahadevan,Matthew M Tran,Steven A. Kushner,Melanie A. Woodin,Paul W. Frankland,Sheena A. Josselyn +12 more
TL;DR: The results indicate that neuronal memory allocation is based on relative neuronal excitability immediately before training, and that neurons with increased CREB are critical components of the memory trace.
Journal ArticleDOI
Towards deep learning with segregated dendrites
TL;DR: Guerguiev et al. as mentioned in this paper showed that artificial neurons more like those in the brain can enable deep learning and suggested that our own neurons may have evolved their shape to support this process.
Posted Content
Towards deep learning with segregated dendrites
TL;DR: It is shown that a deep learning algorithm that utilizes multi-compartment neurons might help to understand how the neocortex optimizes cost functions, and the algorithm takes advantage of multilayer architectures to identify useful higher-order representations—the hallmark of deep learning.