| Understanding Dimensional Collapse in Contrastive Self-supervised Learning | 0 | 0.34 | 2022 |
| Deep learning, reinforcement learning, and world models | 0 | 0.34 | 2022 |
| Barlow Twins: Self-Supervised Learning via Redundancy Reduction | 0 | 0.34 | 2021 |
| Unsupervised Image Matching And Object Discovery As Optimization | 2 | 0.35 | 2019 |
| Inspirational Adversarial Image Generation. | 0 | 0.34 | 2019 |
| The role of over-parametrization in generalization of neural networks. | 4 | 0.38 | 2019 |
| Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation. | 0 | 0.34 | 2018 |
| GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations. | 4 | 0.39 | 2018 |
| A Spectral Regularizer for Unsupervised Disentanglement. | 0 | 0.34 | 2018 |
| Comparing Dynamics: Deep Neural Networks versus Glassy Systems. | 10 | 0.52 | 2018 |
| Backpropagation for Implicit Spectral Densities. | 0 | 0.34 | 2018 |
| GLoMo - Unsupervised Learning of Transferable Relational Graphs. | 1 | 0.34 | 2018 |
| Model-Based Planning in Discrete Action Spaces. | 5 | 0.41 | 2017 |
| Energy-based Generative Adversarial Network. | 168 | 5.51 | 2017 |
| Recurrent Orthogonal Networks and Long-Memory Tasks. | 21 | 0.94 | 2016 |
| Fast Incremental Learning for Off-Road Robot Navigation. | 0 | 0.34 | 2016 |
| Orthogonal RNNs and Long-Memory Tasks. | 1 | 0.36 | 2016 |
| A Mathematical Motivation for Complex-Valued Convolutional Networks. | 12 | 0.60 | 2016 |
| 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings | 0 | 0.34 | 2016 |
| Singularity of the Hessian in Deep Learning. | 0 | 0.34 | 2016 |
| Deep multi-scale video prediction beyond mean square error | 224 | 6.49 | 2015 |
| Open Problem: The landscape of the loss surfaces of multilayer networks | 6 | 0.41 | 2015 |
| Universality in halting time and its applications in optimization | 1 | 0.43 | 2015 |
| Deep Convolutional Networks on Graph-Structured Data | 158 | 4.56 | 2015 |
| Learning to Linearize Under Uncertainty | 43 | 1.90 | 2015 |
| Deep learning with Elastic Averaging SGD. | 0 | 0.34 | 2015 |
| Unsupervised Feature Learning from Temporal Data. | 0 | 0.34 | 2015 |
| High Performance Computer Acoustic Data Accelerator: A New System for Exploring Marine Mammal Acoustics for Big Data Applications | 5 | 0.92 | 2015 |
| Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches | 21 | 0.59 | 2015 |
| Audio Source Separation with Discriminative Scattering Networks. | 0 | 0.34 | 2015 |
| Universum Prescription: Regularization Using Unlabeled Data | 0 | 0.34 | 2015 |
| Explorations on high dimensional landscapes. | 0 | 0.34 | 2015 |
| Text Understanding from Scratch. | 90 | 4.21 | 2015 |
| Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation. | 230 | 16.58 | 2014 |
| Signal recovery from Pooling Representations. | 0 | 0.34 | 2014 |
| The Loss Surfaces of Multilayer Networks. | 12 | 0.47 | 2014 |
| Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation. | 243 | 8.87 | 2014 |
| Causal Graph-Based Video Segmentation | 7 | 0.63 | 2013 |
| Discriminative Recurrent Sparse Auto-Encoders | 0 | 0.34 | 2013 |
| Understanding Deep Architectures using a Recursive Convolutional Network. | 24 | 4.48 | 2013 |
| Fast Training of Convolutional Networks through FFTs. | 12 | 2.67 | 2013 |
| Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients | 5 | 0.65 | 2013 |
| NeuFlow: Dataflow vision processing system-on-a-chip | 23 | 1.24 | 2012 |
| Fast approximations to structured sparse coding and applications to object classification | 6 | 0.43 | 2012 |
| Deep Learning Made Easier by Linear Transformations in Perceptrons. | 52 | 27.40 | 2012 |
| Road scene segmentation from a single image | 69 | 2.67 | 2012 |
| Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers | 74 | 5.93 | 2012 |
| Learning invariant feature hierarchies | 13 | 0.62 | 2012 |
| Learning Representations by Maximizing Compression | 7 | 0.97 | 2011 |
| Efficient Learning of Sparse Invariant Representations | 3 | 0.40 | 2011 |
