Predictive Coding Approximates Backprop along Arbitrary Computation Graphs
Comments Submitted to NeurIPS 2020. Updated Acknowledgements. 11/06/20: fixed typos in maths -- 11/07/20: minor corrections; 05/10/20: major rewrite for ICLR
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness
Comments Accepted paper at EMNLP 2020 and ICLR 2020 BAICS workshop (Oral)
Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee
Comments International Conference on Learning Representations (ICLR) 2020
Learning Space Partitions for Nearest Neighbor Search
Comments ICLR 2020
Afro-MNIST: Synthetic generation of MNIST-style datasets for low-resource languages
Comments 10 pages, 11 figures, presented as a workshop paper at Practical Machine Learning for Developing Countries @ ICLR 2020
Certified Defenses for Adversarial Patches
Comments International Conference on Learning Representations, ICLR 2020
On the Equivalence between Positional Node Embeddings and Structural Graph Representations
Comments This version corrects some typos in the definition of Σ, it should be Σ_n. Code available at https://github.com/PurdueMINDS/Equivalence
Journal ref Published as a conference paper at the Eighth International Conference on Learning Representations (ICLR 2020)
Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain
Comments Published as a conference paper at ICLR 2017
Population Mapping in Informal Settlements with High-Resolution Satellite Imagery and Equitable Ground-Truth
Comments ML-IRL workshop at ICLR 2020
Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
Comments ICLR 2018
A Variational Inequality Perspective on Generative Adversarial Networks
Comments Appears in: Proceedings of the Seventh International Conference on Learning Representations (ICLR 2019). Minor modifications with respect to the ICLR version (First paragraph of page 2 and section 3.3): New reference [Popov 1980] and discussion with regards to the novelty of extrapolation from the past. 38 pages
Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
Comments 17 pages. Accepted by ICLR 2020. Final version (fix typo in figure)
ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
Comments ICLR 2020 paper. Project page: http://whyu.me/reclor/
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
Comments Published as a conference paper at ICLR 2019
Amortized learning of neural causal representations
Comments ICLR 2020 causal learning for decision making workshop
Modeling, Visualization, and Analysis of African Innovation Performance
Comments 4 pages, 3 figures, Appeared as a poster presentation at the Practical Machine Learning for Developing Countries workshop in the 2020 International Conference on Learning Representation (ICLR), formerly Addis Ababa, held virtually, slides and corresponding video for virtual sessions can be found at: https://pml4dc.github.io/iclr2020/program/pml4dc_47.html
Supervised Community Detection with Line Graph Neural Networks
Comments Published at International Conference on Learning Representations (ICLR 2019)
Picking Winning Tickets Before Training by Preserving Gradient Flow
Comments Fix several typos
Journal ref In Proceedings of the 8th International Conference on Learning Representations (ICLR), 2020
Regularized Learning for Domain Adaptation under Label Shifts
Comments International Conference on Learning Representations (ICLR) 2019
Lagrangian Neural Networks
Comments 7 pages (+2 appendix). Published in ICLR 2020 Deep Differential Equations Workshop. Code at github.com/MilesCranmer/lagrangian_nns
End-to-end Optimized Image Compression
Comments Published as a conference paper at ICLR 2017
Journal ref Presented at: Int'l Conf on Learning Representations, Toulon, France, April 2017
Geodesics of learned representations
Comments Published as a conference paper at ICLR 2016
Journal ref Presented at: Int'l Conf on Learning Representations (ICLR), San Juan, Puerto Rico, May 2016
Critical initialisation in continuous approximations of binary neural networks
Journal ref ICLR 2020
Learning Nearly Decomposable Value Functions Via Communication Minimization
Comments 8th International Conference on Learning Representations (ICLR 2020)
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
Comments ICLR 2020
The Gambler's Problem and Beyond
Comments International Conference on Learning Representations (ICLR) 2020
Excessive Invariance Causes Adversarial Vulnerability
Journal ref Proceedings of the 7th International Conference on Learning Representations (ICLR), 2019
Meta-Learning Probabilistic Inference For Prediction
Comments International Conference on Learning Representations (ICLR) 2019
Journal ref International Conference on Learning Representations (2019)
A Data and Compute Efficient Design for Limited-Resources Deep Learning
Comments Accepted for poster presentation at the Practical Machine Learning for Developing Countries (PML4DC) workshop, ICLR 2020
An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality
Comments 11 pages (+18 appendix). Published as a conference paper at ICLR 2020. https://openreview.net/forum?id=HJeiDpVFPr
