13 questions · 5 almanac · 2 findings

Deep Learning and Neural Networks

Learning with multilayer artificial neural networks.

Almanac Building and Doubting the Thinking Machine
  • What did Minsky and Papert's book Perceptrons prove about single-layer neural networks?
  • Why did Perceptrons cool enthusiasm for connectionist AI approaches for a decade?
Almanac The Quiet Years Before Everyone Was Listening
  • Why were artificial neural networks considered a disappointment through the 1990s and 2000s?
  • What specific contributions did Hinton, LeCun, and Bengio each make to deep learning before it became mainstream?
  • How did the AlexNet breakthrough at the 2012 ImageNet competition change the field's attention to deep learning?
Almanac A Landscape of Valleys for Memory
  • What is a Boltzmann machine, and how did it extend Hopfield's physical intuition about neural networks?
  • Why did backpropagation applied to multi-layer neural networks become the technique that made deep learning work at scale?
Finding Deep Learning for Cognitive Neuroscience
  • How can deep neural network models serve as testable, end-to-end trainable implementations of cognitive theories?
  • In what ways can insights from deep learning models inform the design of instructional and learning technology systems?