Hierarchical Latent Semantic Mapping for Automated Topic Generation
Comments 9 pages, 3 figures, Under Review as a conference at ICLR 2016
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
L1 logistic regression as a feature selection step for training stable classification trees for the prediction of severity criteria in imported malaria
Comments 18 pages, 10 figures, ICLR, computational science - Learning, Imported Malaria, L1 logistic regression, Decision tree
Dynamic Adaptive Network Intelligence
Comments 8 pages, 2 figures, 3 tables, ICLR 2016 conference paper submission
AUC-maximized Deep Convolutional Neural Fields for Sequence Labeling
Comments Under review as a conference paper at ICLR 2016
ParseNet: Looking Wider to See Better
Comments ICLR 2016 submission
Flattened Convolutional Neural Networks for Feedforward Acceleration
Comments International Conference on Learning Representations (ICLR) 2015
Adjustable Bounded Rectifiers: Towards Deep Binary Representations
Comments Under review as a conference paper at ICLR 2016
Multilingual Image Description with Neural Sequence Models
Comments Under review as a conference paper at ICLR 2016
How far can we go without convolution: Improving fully-connected networks
Comments 10 pages, 11 figures, submitted for ICLR 2016
Symmetry-invariant optimization in deep networks
Comments Submitted to ICLR 2016. arXiv admin note: text overlap with arXiv:1511.01029
ADASECANT: Robust Adaptive Secant Method for Stochastic Gradient
Comments 8 pages, 3 figures, ICLR workshop submission
Training deep neural networks with low precision multiplications
Comments 10 pages, 5 figures, Accepted as a workshop contribution at ICLR 2015
Parallel training of DNNs with Natural Gradient and Parameter Averaging
Comments Accepted as workshop contribution to ICLR 2015. 12 pages plus 16 pages of appendices, International Conference on Learning Representations (ICLR): Workshop track, 2015. [2 sets of minor fixes post-publication.]
Representation Learning for cold-start recommendation
Comments Accepted as workshop contribution at ICLR 2015
Discovering Hidden Factors of Variation in Deep Networks
Comments Presented at International Conference on Learning Representations 2015 Workshop
Variational Recurrent Auto-Encoders
Comments Accepted at ICLR workshop track
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
Comments Add a simple strategy to boost the performance of image captioning task significantly. More details are shown in Section 8 of the paper. The code and related data are available at https://github.com/mjhucla/mRNN-CR ;. arXiv admin note: substantial text overlap with arXiv:1410.1090
Journal ref ICLR 2015
On distinguishability criteria for estimating generative models
Comments This version adds a figure that appeared on the poster at ICLR, changes the template to say that the paper was accepted as a workshop contribution (previously it was under a review as a conference submission), and fixes some typos
Modeling Compositionality with Multiplicative Recurrent Neural Networks
Comments 10 pages, 2 figures, published at ICLR 2015
Word Representations via Gaussian Embedding
Comments 12 pages, published as conference paper at ICLR 2015
Learning Non-deterministic Representations with Energy-based Ensembles
Comments 9 pages, 3 figures, ICLR-15 workshop contribution
Entity-Augmented Distributional Semantics for Discourse Relations
Comments Accepted as a workshop contribution at ICLR 2015
Provable Methods for Training Neural Networks with Sparse Connectivity
Comments Accepted for presentation at Neural Information Processing Systems(NIPS) 2014 Deep Learning workshop and Accepted as a workshop contribution at ICLR 2015
A Group Theoretic Perspective on Unsupervised Deep Learning
Comments 2-page version of arXiv:1412.6621 prepared for presentation at ICLR 2015 workshop as required by ICLR PC). This version has some minor formatting changes as required by the conference
Learning Activation Functions to Improve Deep Neural Networks
Comments Accepted as a workshop paper contribution at the International Conference on Learning Representations (ICLR) 2015
Score Function Features for Discriminative Learning
Comments Accepted as a workshop contribution at ICLR 2015. A longer version of this work is also available on arXiv: http://arxiv.org/abs/1412.2863
A Generative Model for Deep Convolutional Learning
Comments 3 pages, 1 figure, ICLR workshop
Learning linearly separable features for speech recognition using convolutional neural networks
Comments Final version for ICLR 2015 Workshop; Revisions according to reviews. Revised Section 4.5. Add references and correct typos. Submitted for ICLR 2015 conference track
Diverse Embedding Neural Network Language Models
Comments Under review as workshop contribution at ICLR 2015
Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations
Comments Accepted as a workshop contribution at ICLR 2015
