Quasi-Recurrent Neural Networks
Comments Submitted to conference track at ICLR 2017
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Deep Convolutional Neural Network Design Patterns
Comments Submitted as a conference paper at ICLR 2017
Song From PI: A Musically Plausible Network for Pop Music Generation
Comments under review at ICLR 2017
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
Comments 14 pages. Under review as a conference paper at ICLR 2017
Generative Adversarial Nets from a Density Ratio Estimation Perspective
Comments Add contents especially theoretical things for ICLR 2017
Importance Weighted Autoencoders
Comments Submitted to ICLR 2015
Generative Adversarial Networks as Variational Training of Energy Based Models
Comments Under review at ICLR 2017
What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
Comments The verison submitted to ICLR
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Comments In ICLR Format
Hardware-oriented Approximation of Convolutional Neural Networks
Comments 8 pages, 4 figures, Accepted as a workshop contribution at ICLR 2016. Updated comparison to other works
Surprisal-Driven Feedback in Recurrent Networks
Comments ICLR 2017 submission, fixed some equations
Learning Genomic Representations to Predict Clinical Outcomes in Cancer
Comments ICLR 2016 Workshop Track- May 2nd 2016 International Conference on Learning Representations
Data-dependent Initializations of Convolutional Neural Networks
Comments ICLR 2016
Unifying distillation and privileged information
Journal ref Proceedings of the International Conference on Learning Representations (2016) 1-10
Neural Programmer: Inducing Latent Programs with Gradient Descent
Comments Accepted as a conference paper at ICLR 2015
Unsupervised Learning with Imbalanced Data via Structure Consolidation Latent Variable Model
Comments ICLR 2016 Workshop
Improving performance of recurrent neural network with relu nonlinearity
Comments 10 pages 6 figures; under consideration for publication with ICLR 2016
Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance
Comments This paper accepted in ICLR 2016 main conference
Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series
Comments Accepted as workshop paper at ICLR 2016; accepted as workshop paper for anomaly detection workshop at ICML 2016
Distributional Smoothing with Virtual Adversarial Training
Comments Under review as a conference paper at ICLR 2016
Reducing Overfitting in Deep Networks by Decorrelating Representations
Comments 12 pages, 5 figures, 5 tables, Accepted to ICLR 2016, (v4 adds acknowledgements)
Neural Machine Translation by Jointly Learning to Align and Translate
Comments Accepted at ICLR 2015 as oral presentation
Compressing Word Embeddings
Comments 10 pages, 0 figures, submitted to ICONIP-2016. Previous experimental results were submitted to ICLR-2016, but the paper has been significantly updated, since a new experimental set-up worked much better
On-the-fly Network Pruning for Object Detection
Comments Accepted at ICLR 2016 workshop track as a poster presentation
Learning to decompose for object detection and instance segmentation
Comments ICLR 2016 Workshop
Multi-Scale Context Aggregation by Dilated Convolutions
Comments Published as a conference paper at ICLR 2016
Scale Normalization
Comments Preliminary version submitted to ICLR workshop 2016
Neural network-based clustering using pairwise constraints
Comments ICLR 2016
A Minimalistic Approach to Sum-Product Network Learning for Real Applications
Comments Accepted to ICLR 2016 workshop track
Online Batch Selection for Faster Training of Neural Networks
Comments Workshop paper at ICLR 2016
