Unsupervised Representation Learning

Unsupervised Representation Learning

Simons Institute via YouTube Direct link

Seven Strategies to Shape the Energy Function

12 of 16

12 of 16

Seven Strategies to Shape the Energy Function

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Unsupervised Representation Learning

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Deep Learning = Learning Hierarchical Representations
  3. 3 Mask R-CNN: instance segmentation
  4. 4 What is Common Sense?
  5. 5 Common Sense is the ability to fill in the blanks
  6. 6 How Much Information Does the Machine Need to
  7. 7 Training the Actor with Optimized Action Sequences
  8. 8 Augmenting Neural Nets with a Memory Module
  9. 9 Memory/Stack-Augmented Recurrent Nets
  10. 10 Entity Recurrent Neural Net
  11. 11 Energy-Based Unsupervised Learning
  12. 12 Seven Strategies to Shape the Energy Function
  13. 13 constant volume of low energy Energy surface for PCA and K-means 1. build the machine so that the volume of low energy stuff is constant
  14. 14 use a regularizer that limits do the volume of space that has low energy Sparse coding, sparse auto-encoder, Predictive Sparse Decomposition
  15. 15 The Hard Part: Prediction Under Uncertainty Invariant prediction: The training samples are merely representatives of a whole set of possible outputs (eg, a manifold of outputs).
  16. 16 Video Prediction: predicting 5 frames

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.