hulalazz / cambridge-ai

SIPB Deep Learning Group

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.

Suggested Papers:

• 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

Schedule:

Date	Paper	Implementation
12.7.16	InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
12.14.16	Key-Value Memory Networks for Directly Reading Documents
12.21.16	StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
1.17.17	Neural Semantic Encoders
1.24.17	Understanding Deep Learning Requires Rethinking Generalization
1.31.17	Mastering the Game of Go with Deep Networks
2.7.17	Towards Principled Methods for Training GANs
2.14.17	Wasserstein GAN
3.7.17	Neural Programmer Interpreters
3.21.17	Image-to-Image Translation with Conditional Adversarial Networks
3.28.17	Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
4.4.17	End to End Learning for Self-Driving Cars
4.18.17	Massive Exploration of Neural Machine Translation Architectures
4.25.17	Strategic Attentive Writer for Learning Macro-Actions
5.4.17	Using Fast Weights to Attend to the Recent Past
5.9.17	Improved Training of Wasserstein GANs	code
5.16.17	Trust Region Policy Optimization	modular_rl
5.23.17	Emergence of Grounded Compositional Language in Multi-Agent Populations
5.30.17	High-Dimensional Continuous Control Using Generalized Advantage Estimation	modular_rl
6.6.17	Artistic style transfer for videos	artistic video
6.13.17	Lie-Access Neural Turing Machines	harvardnlp
6.20.17	Neural Episodic Control	PFCM
7.11.17	Speaker diarization using deep neural network embeddings
7.18.17	A simple neural network module for relational reasoning	relation-network
7.25.17	Decoupled Neural Interfaces using Synthetic Gradients & follow-up	dni.pytorch
8.1.17	Full-Capacity Unitary Recurrent Neural Networks	complex_RNN, urnn
8.8.17	Hyper Networks	otoro blog
8.15.17	Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences	plstm
8.22.17	Designing Neural Network Architectures using Reinforcement Learning	metaqnn
8.29.17	Deep Transfer Learning with Joint Adaptation Networks	jmmd.{cpp,hpp}
9.5.17	Recurrent Dropout Without Memory Loss	rnn_cell_mulint_modern.py
9.12.17	Neuroscience-inspired AI
9.19.17	Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks	cbfinn
9.26.17	Variational Boosting: Iteratively Refining Posterior Approximations	vboost
10.10.17	Zero-Shot Learning Through Cross-Modal Transfer	zslearning
10.17.17	What does Attention in Neural Machine Translation Pay Attention to?
10.24.17	Poincaré Embeddings for Learning Hierarchical Representations	poincare_embeddings
11.7.17	Meta-Learning with Memory-Augmented Neural Networks	ntm-meta-learning
11.14.17	Mastering the game of Go without human knowledge
11.28.17	Emergent Complexity via Multi-Agent Competition (blog post)	multiagent-competition
12.5.17	Stochastic Neural Networks for Hierarchical Reinforcement Learning	snn4hrl
12.12.17	Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks	(ChainsofReasoning)
1.9.18	Intro to Coq
1.16.18	Go for a Walk and Arrive at the Answer, RelNet: End-to-End Modeling of Entities & Relations
1.23.18	Visualizing The Loss Landscape Of Neural Nets
1.30.18	The Case for Learned Index Structures