ICML 2016 Workshop on Neural Networks Back To The Future
TechTalks from event: ICML 2016 Workshop on Neural Networks Back To The Future
- All Talks
- Machine Learning and Neural Nets at Bell Labs, Holmdel
- On TD-Learning and links with DeepRL in Atari and AlphaGo
- Learning Long-Term Dependencies with Gradient Descent is Difficult
- Recurrent Neural Networks: State Machines and Pushdown Automata
- Panel Discussion
- Backpropagation without Multiplication
- Tangent Propagation
- Let your Network Grow
- Automatic Differentiation versus Back-Propagation: The Human Touch
- Graph Transformer Networks