46 min listen
BI 009 Blake Richards: Deep Learning in the Brain
FromBrain Inspired
ratings:
Length:
71 minutes
Released:
Sep 13, 2018
Format:
Podcast episode
Description
Mentioned in the show
Follow Blake on twitter: @tyrell_turing
Blake’s Learning in Neural Circuits (LiNC) Laboratory.
He’s a Fellow with the Learning in Machines and Brains Program of the Canadian Institute for Advanced Research (CIFAR).
The paper we discuss:
Towards Deep Learning With Segregated Dendrites.
Code to run the model on Github.
If you’d rather watch a talk, here’s the same topic in a great talk by Blake.
The idea of approaching neuroscience from the perspective there are general principles of computation applicable to both brains and AI:
Geoffrey Hinton.
Cybernetics.
McCullough and Pitts artificial neuron: Their original paper and a nice tutorial.
Frank Rosenblaut.
Demis Hassabis, who founded Deepmind, wrote a great review of how AI and neuroscience can work together.
Donald Hebb of the famed Hebbian Learning in his famous book The Organization of Behavior: A Neuropsychological Theory.
Konrad Kording’s 2001 paper articulating the same idea we discuss: Supervised and Unsupervised Learning with Two Sites of Synaptic Integration.
MNIST dataset of handwritten digits – used to train and test a lot of machine learning networks.
Eliminative Materialism, the idea our common sense conception of the mind is false.
Follow Blake on twitter: @tyrell_turing
Blake’s Learning in Neural Circuits (LiNC) Laboratory.
He’s a Fellow with the Learning in Machines and Brains Program of the Canadian Institute for Advanced Research (CIFAR).
The paper we discuss:
Towards Deep Learning With Segregated Dendrites.
Code to run the model on Github.
If you’d rather watch a talk, here’s the same topic in a great talk by Blake.
The idea of approaching neuroscience from the perspective there are general principles of computation applicable to both brains and AI:
Geoffrey Hinton.
Cybernetics.
McCullough and Pitts artificial neuron: Their original paper and a nice tutorial.
Frank Rosenblaut.
Demis Hassabis, who founded Deepmind, wrote a great review of how AI and neuroscience can work together.
Donald Hebb of the famed Hebbian Learning in his famous book The Organization of Behavior: A Neuropsychological Theory.
Konrad Kording’s 2001 paper articulating the same idea we discuss: Supervised and Unsupervised Learning with Two Sites of Synaptic Integration.
MNIST dataset of handwritten digits – used to train and test a lot of machine learning networks.
Eliminative Materialism, the idea our common sense conception of the mind is false.
Released:
Sep 13, 2018
Format:
Podcast episode
Titles in the series (100)
BI 005 David Sussillo: RNNs are Back!: Mentioned in the show: David’s Twitter account Papers we discuss: Sussillo, D.S. & Abbott, L. F. (2009). Generating Coherent Patterns of Activity from Chaotic Neural Networks. Neuron 63(4). Sussillo, D. (2014) Neural circuits as computational by Brain Inspired