Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks
Comments Published as a conference paper in ICLR 2019
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods
Comments To appear in ICLR 2019. arXiv admin note: text overlap with arXiv:1806.06939
Kernel Change-point Detection with Auxiliary Deep Generative Models
Comments To appear in ICLR 2019
Sample Efficient Adaptive Text-to-Speech
Comments Accepted by ICLR 2019
Hierarchical interpretations for neural network predictions
Comments Published in ICLR 2019
Journal ref ICLR 2019
Neural probabilistic motor primitives for humanoid control
Comments Accepted as a conference paper at ICLR 2019
Hierarchical visuomotor control of humanoids
Comments Accepted as a conference paper at ICLR 2019
Learning Representations of Sets through Optimized Permutations
Comments Published in ICLR 2019
Neural network gradient-based learning of black-box function interfaces
Comments Published as a conference paper at ICLR 2019
On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks
Comments Published in ICLR 2019
ADef: an Iterative Algorithm to Construct Adversarial Deformations
Comments ICLR 2019 conference paper. 25 pages, 20 figures
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Comments ICLR 2019, code is available at https://github.com/chihyaoma/selfmonitoring-agent
Revealing interpretable object representations from human behavior
Comments Accepted in ICLR 2019
Efficient Lifelong Learning with A-GEM
Comments Published as a conference paper at ICLR 2019
h-detach: Modifying the LSTM Gradient Towards Better Optimization
Comments First two authors contributed equally. Published in ICLR 2019
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
Comments ICLR 2019 Conference Paper
Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation
Comments Accepted as a conference paper at ICLR 2019
Spherical CNNs on Unstructured Grids
Comments Accepted as a conference paper at ICLR 2019. Codes available at https://github.com/maxjiang93/ugscnn
Efficient Convolutional Neural Network Training with Direct Feedback Alignment
Comments The paper was submitted to ICLR 2019
MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
Comments Published at ICLR-2019. 12 pages contents + 4 pages appendix, 5 figures
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Comments ICLR 2019, project page: https://people.eecs.berkeley.edu/~janner/o2p2/
Quaternion Recurrent Neural Networks
Comments ICLR Update - Full rework
An analytic theory of generalization dynamics and transfer learning in deep linear networks
Comments ICLR 2019, 20 pages
Decoupled Weight Decay Regularization
Comments Published as a conference paper at ICLR 2019
A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs
Journal ref International Conference on Learning Representations, 2019 https://openreview.net/forum?id=S1xq3oR5tQ
SOM-VAE: Interpretable Discrete Representation Learning on Time Series
Comments Accepted for publication at the Seventh International Conference on Learning Representations (ICLR 2019)
Generating Multiple Objects at Spatially Distinct Locations
Comments Published at ICLR 2019
Multi-class Classification without Multi-class Labels
Comments International Conference on Learning Representations (ICLR 2019)
InstaGAN: Instance-aware Image-to-Image Translation
Comments Accepted to ICLR 2019. High resolution images are available in https://github.com/sangwoomo/instagan
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm
Comments Published as a conference paper in ICLR 2019
