Blake Aaron Richards

Blake Aaron Richards

Auto-generated profile, based on publicly available information

Blake Aaron Richards

McGill University

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2019 in Nature Neuroscience
Verified
Journal Article
Closed access
PDF file
BRBlake A. Richards
Blake A. Richards
TLTimothy P. Lillicrap
Timothy P. Lillicrap
PBPhilippe Beaudoin
Philippe Beaudoin
YBYoshua Bengio
Yoshua Bengio
RBRafal Bogacz
Rafal Bogacz
KKKonrad P. Kording
Konrad P. Kording

9 May 2014 in Science
Verified
Journal Article
Closed access
PDF file
KAKatherine G. Akers
Katherine G. Akers
ACAlonso Martinez Canabal
Alonso Martinez Canabal
LRLeonardo Restivo
Leonardo Restivo
AYAdelaide P. Yiu
Adelaide P. Yiu
ACAntonietta De Cristofaro
Antonietta De Cristofaro
PFPaul W. Frankland
Paul W. Frankland
Forget It!: When examining the relationship between the production of new neurons in the hippocampus and memory, studies have generally first manipulated hippocampal neurogenesis and afterward investigated memory formation and found that new neurons help to encode new memories. However, when investigating how similar manipulations of neurogenesis impact established hippocampus-dependent memories, Akers et al. (p. 598 ; see the Perspective by Mongiat and Schinder ) uncovered a role for neurogenesis in memory clearance. Thus, the continuous addition of new neurons both degrades existing information stored in hippocampal circuits and simultaneously provides substrates for new learning.

5 December 2017 in eLife
Verified
Journal Article
Open access
JGJordan Guerguiev
Jordan Guerguiev
TLTimothy P Lillicrap
Timothy P Lillicrap
BRBlake A Richards
Blake A Richards
Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations—the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons.

1 August 2014 in Neuron
Verified
Journal Article
Closed access
AYAdelaide P. Yiu
Adelaide P. Yiu
VMValentina Mercaldo
Valentina Mercaldo
CYChen Yan
Chen Yan
BRBlake Richards
Blake Richards
ARAsim J. Rashid
Asim J. Rashid
SJSheena A. Josselyn
Sheena A. Josselyn

13 May 2021 in Nature Neuroscience
Verified
Journal Article
Closed access
PDF file
APAlexandre Payeur
Alexandre Payeur
JGJordan Guerguiev
Jordan Guerguiev
FZFriedemann Zenke
Friedemann Zenke
BRBlake A. Richards
Blake A. Richards
RNRichard Naud
Richard Naud

25 August 2020 in Nature Communications
Verified
Journal Article
Open access
PDF file
MSMarc-Andre Schulz
Marc-Andre Schulz
BYB.T. Thomas Yeo
B.T. Thomas Yeo
JVJoshua T. Vogelstein
Joshua T. Vogelstein
JMJanaina Mourao-Miranada
Janaina Mourao-Miranada
JKJakob N. Kather
Jakob N. Kather
DBDanilo Bzdok
Danilo Bzdok
Recently, deep learning has unlocked unprecedented success in various domains, especially using images, text, and speech. However, deep learning is only beneficial if the data have nonlinear relationships and if they are exploitable at available sample sizes. We systematically profiled the performance of deep, kernel, and linear models as a function of sample size on UKBiobank brain images against established machine learning references. On MNIST and Zalando Fashion, prediction accuracy consistently improves when escalating from linear models to shallow-nonlinear models, and further improves with deep-nonlinear models. In contrast, using structural or functional brain scans, simple linear models perform on par with more complex, highly parameterized models in age/sex prediction across increasing sample sizes. In sum, linear models keep improving as the sample size approaches ~10,000 subjects. Yet, nonlinearities for predicting common phenotypes from typical brain scans remain largely inaccessible to the examined kernel and deep learning methods.