Enable JavaScript to see more content

Related: TFIDF
[1706.04769] Stochastic Training of Neural Networks via Successive Convex Approximations[1807.05292] Neural Networks Regularization Through Representation Learning[1809.01465] Deep Bilevel Learning[1909.12398] Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization offers Significant Performance and Efficiency Gains[1910.08475] On the Difficulty of Warm-Starting Neural Network Training[1908.10920] Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective[1908.10920v1] Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective[1906.12005] Rényi Fair Inference
Mentions
[1603.04467] TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems[1603.03116] Low-rank passthrough neural networks[1710.09282] A Survey of Model Compression and Acceleration for Deep Neural Networks[1412.1442] Memory Bounded Deep Convolutional Networks[1706.04638] Proximal Backpropagation[1506.07540] Global Optimality in Tensor Factorization, Deep Learning, and Beyond[1510.00149] Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding[1704.04861] MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications[1506.08473] Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods[1412.6980] Adam: A Method for Stochastic Optimization[1607.00345] Convergence Rate of Frank-Wolfe for Non-Convex Objectives[1706.02025] Imposing Hard Constraints on Deep Networks: Promises and Limitations[1412.7753] Learning Longer Memory in Recurrent Neural Networks[1705.08302] Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation[1702.03849] Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis[1706.05098] An Overview of Multi-Task Learning in Deep Neural Networks[1605.08361] No bad local minima: Data independent training error guarantees for multilayer neural networks[1511.06067] Convolutional neural networks with low-rank regularization
Related: Semantic Math
[1603.06788] Adaptive Parameter Selection in Evolutionary Algorithms by Reinforcement Learning with Dynamic Discretization of Parameter Range[1710.10466] Scale-Robust Localization Using General Object Landmarks[1810.11197] Lossless (and Lossy) Compression of Random Forests[1610.06656] Single Pass PCA of Matrix Products[1412.7062] Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs[1705.08236] 3D Convolutional Neural Networks for Brain Tumor Segmentation: A Comparison of Multi-resolution Architectures[1812.01664] A Stable Cardinality Distance for Topological Classification[1809.08621] Learning and Evaluating Sparse Interpretable Sentence Embeddings[1404.3418] Active Learning for Undirected Graphical Model Selection[1703.04336] A Visual Representation of Wittgenstein's Tractatus Logico-Philosophicus