Completed
Update Parameters with the Policy Gradient
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Backpropagation and Deep Learning in the Brain
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 The credit assignment problem
- 3 The solution in artificial networks: backprop
- 4 Why Isn't Backprop "Biologically Plausible"?
- 5 Neuroscience Evidence for Backprop in the Brain?
- 6 A spectrum of credit assignment algorithms
- 7 How to convince a neuroscientist that the cortex is learning via [something like] backprop
- 8 What about reinforcement learning?
- 9 A Single Trial of Reinforcement Learning
- 10 Measuring Outcomes
- 11 Update Parameters with the Policy Gradient
- 12 Training Neural Networks with Policy Gradients
- 13 The backpropagation solution (AKA 'Weight transport)
- 14 Feedback alignment
- 15 Energy based models.
- 16 Question
- 17 Constraints on learning rules.
- 18 Target propagation
- 19 Gradient free DTP variants
- 20 Performance on ImageNet
- 21 New Models of a Neuron
- 22 Future Directions
- 23 Difference target-propagation (DTP)
