The schedule of readings for the SIPB/Cambridge AI Deep Learning Group If you have any papers you'd like to discuss, please either make a pull request, or send an email to the group and we'll add it. Papers with implementations available are strongly preferred.
- Improving speech recognition by revising gated recurrent units
- A systematic study of the class imbalance problem in convolutional neural network
- Designing Neural Network Architectures using Reinforcement Learning (Implementation)
- Accompanying paper: Practical Neural Network Performance Prediction for Early Stopping
- Toward an Integration of Deep Learning and Neuroscience (Potential companion paper to "Neuroscience-inspired AI")
- Label, Segment, Featurize: a cross domain framework for prediction engineering
- Learning to Infer Graphics Programs from Hand-Drawn Images and supplement.
- Information Dropout: Learning Optimal Representations Through Noisy Computation. (Implementation).
- On the emergence of invariance and disentangling in deep representations.
- Reinforcement Learning with Deep Energy-Based Policies. (Blog, Code, Videos)
- Meta-Learning Shared Hierarchies. Implementation
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition.
- Dynamic Routing Between Capsules
- Opening the black box of Deep Neural Networks via Information