Hybrid Models for Learning to Branch
Comments 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada
作者
Yoshua Bengio
Machine Learning
NU-GAN: High resolution neural upsampling with GAN
CLOSURE: Assessing Systematic Generalization of CLEVR Models
Comments Technical report
Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
Comments published at ECCV 2020
Visual Concept Reasoning Networks
Comments Preprint
Learning Neural Causal Models from Unknown Interventions
Deriving Differential Target Propagation from Iterating Approximate Inverses
Mastering Rate based Curriculum Learning
BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization
BabyAI 1.1
Comments 9 pages, 1 figure, technical report
COVI White Paper
Comments 64 pages, 1 figure
GMNN: Graph Markov Neural Networks
Comments icml 2019
Revisiting Fundamentals of Experience Replay
Comments Published at ICML 2020. First two authors contributed equally and code available at https://github.com/google-research/google-research/tree/master/experience_replay
HNHN: Hypergraph Networks with Hyperedge Neurons
Journal ref Graph Representation Learning and Beyond Workshop at ICML 2020
S2RMs: Spatially Structured Recurrent Modules
Rethinking Distributional Matching Based Domain Adaptation
Comments Preprint version
Perceptual Generative Autoencoders
Predicting COVID-19 Pneumonia Severity on Chest X-ray with Deep Learning
Image-to-image Mapping with Many Domains by Sparse Attribute Transfer
Learning Causal Models Online
Comments Spurious features, causal models, online learning, random search, non-iid
Training End-to-End Analog Neural Networks with Equilibrium Propagation
On Catastrophic Interference in Atari 2600 Games
Comments First two authors contributed equally. Code available to reproduce experiments at https://github.com/google-research/google-research/tree/master/memento
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Comments added the statistics of top-100 compounds used logP metric with scaled components added values of the initial reactants to the box plots some values in tables are recalculated due to the inconsistent environments on different machines. corresponding benchmarks were rerun with the requirements on github. no significant changes in the results. corrected figures in the Appendix
A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM
Comments 6 pages, 1 figure, 1 table, accepted for publication in the 21st International Conference on Artificial Intelligence in Education (AIED 2020)
Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach
Comments ACL20
