ICLR 2015 论文列表3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. |
A Unified Perspective on Multi-Domain and Multi-Task Learning.
Generative Modeling of Convolutional Neural Networks.
Move Evaluation in Go Using Deep Convolutional Neural Networks.
Leveraging Monolingual Data for Crosslingual Compositional Word Representations.
Understanding Locally Competitive Networks.
Automatic Discovery and Optimization of Parts for Image Classification.
Zero-bias autoencoders and the benefits of co-adapting features.
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition.
Modeling Compositionality with Multiplicative Recurrent Neural Networks.
Explaining and Harnessing Adversarial Examples.
Embedding Entities and Relations for Learning and Inference in Knowledge Bases.
Scheduled denoising autoencoders.
Adam: A Method for Stochastic Optimization.
Joint RNN-Based Greedy Parsing and Word Composition.
Transformation Properties of Learned Visual Representations.
Deep Narrow Boltzmann Machines are Universal Approximators.
Multiple Object Recognition with Visual Attention.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs.
Techniques for Learning Binary Stochastic Feedforward Neural Networks.
FitNets: Hints for Thin Deep Nets.
Neural Machine Translation by Jointly Learning to Align and Translate.
Qualitatively characterizing neural network optimization problems.
Object Detectors Emerge in Deep Scene CNNs.
Memory Networks.
The local low-dimensionality of natural images.
Reweighted Wake-Sleep.
Fast Convolutional Nets With fbfft: A GPU Performance Evaluation.
Very Deep Convolutional Networks for Large-Scale Image Recognition.
Deep Structured Output Learning for Unconstrained Text Recognition.
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN).
Word Representations via Gaussian Embedding.