Completed
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 Intro
- 2 Deep Learning = Learning Hierarchical Representations
- 3 Mask R-CNN: instance segmentation
- 4 What is Common Sense?
- 5 Common Sense is the ability to fill in the blanks
- 6 How Much Information Does the Machine Need to
- 7 Training the Actor with Optimized Action Sequences
- 8 Augmenting Neural Nets with a Memory Module
- 9 Memory/Stack-Augmented Recurrent Nets
- 10 Entity Recurrent Neural Net
- 11 Energy-Based Unsupervised Learning
- 12 Seven Strategies to Shape the Energy Function
- 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 use a regularizer that limits do the volume of space that has low energy Sparse coding, sparse auto-encoder, Predictive Sparse Decomposition
- 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 Video Prediction: predicting 5 frames