Purine: A bi-graph based deep learning framework
Comments Submitted to ICLR 2015 workshop
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Fully Convolutional Multi-Class Multiple Instance Learning
Comments in ICLR 2015
Object Detectors Emerge in Deep Scene CNNs
Comments 12 pages, ICLR 2015 conference paper
Hot Swapping for Online Adaptation of Optimization Hyperparameters
Comments Submission to ICLR 2015
Simple Image Description Generator via a Linear Phrase-Based Approach
Comments Accepted as a workshop paper at ICLR 2015
Attention for Fine-Grained Categorization
Comments ICLR 2015 Workshop
Joint RNN-Based Greedy Parsing and Word Composition
Comments Published as a conference paper at ICLR 2015
Striving for Simplicity: The All Convolutional Net
Comments accepted to ICLR-2015 workshop track; no changes other than style
An Analysis of Unsupervised Pre-training in Light of Recent Advances
Comments Accepted as a workshop contribution to ICLR 2015
Scheduled denoising autoencoders
Comments Published as a conference paper at ICLR 2015
Learning Compact Convolutional Neural Networks with Nested Dropout
Comments 4 pages, 2 figures. Accepted as a workshop contribution at ICLR 2015
Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison
Comments Accepted as a workshop contribution at ICLR 2015
N-gram-Based Low-Dimensional Representation for Document Classification
Comments Accepted as a workshop contribution at ICLR 2015
Deep Narrow Boltzmann Machines are Universal Approximators
Comments Published as a conference paper at ICLR 2015
Journal ref http://www.iclr.cc/doku.php?id=iclr2015:main
NICE: Non-linear Independent Components Estimation
Comments 11 pages and 2 pages Appendix, workshop paper at ICLR 2015
Understanding Locally Competitive Networks
Comments 9 pages + 2 supplementary, Accepted to ICLR 2015 Conference track
Training Convolutional Networks with Noisy Labels
Comments Accepted as a workshop contribution at ICLR 2015
Explorations on high dimensional landscapes
Comments 11 pages, 8 figures, workshop contribution at ICLR 2015
Theano-based Large-Scale Visual Recognition with Multiple GPUs
Comments ICLR 2015 workshop camera-ready version
Fast Label Embeddings for Extremely Large Output Spaces
Comments Accepted as a workshop contribution at ICLR 2015
Denoising autoencoder with modulated lateral connections learns invariant representations of natural images
Comments Presentation at ICLR 2015 workshop
Algorithmic Robustness for Learning via $(ε, γ, τ)$-Good Similarity Functions
Comments ICLR 2015 Workshop - accepted
A Unified Perspective on Multi-Domain and Multi-Task Learning
Comments 9 pages, Accepted to ICLR 2015 Conference Track
The local low-dimensionality of natural images
Comments Published as conference paper at ICLR 2015
Learning Stochastic Recurrent Networks
Comments Submitted to conference track of ICLR 2015
Language Recognition using Random Indexing
Comments 7 pages, 1 figures, 2 tables, ICLR 2015
Generative Deep Deconvolutional Learning
Comments 21 pages, 9 figures, revised version for ICLR 2015
Avoiding Confusion between Predictors and Inhibitors in Value Function Approximation
Comments 14 pages, 3 figures, 23 references, Workshop paper in ICLR 2014 (updated based on reviewer comments)
Learning Temporal Dependencies in Data Using a DBN-BLSTM
Comments 6 pages, 2 figures, 1 table, ICLR 2015 conference track submission under review
Audio Source Separation Using a Deep Autoencoder
Comments 3 pages, 4 figures, ICLR 2015
