{"list":"other","total":80,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"1712.00468","title":"Graph Signal Processing: Overview, Challenges and Applications","created":"2017-12-01","cited_by_count":413},{"id":"1809.02165","title":"Deep Learning for Generic Object Detection: A Survey","created":"2018-09-06","cited_by_count":392},{"id":"1901.06523","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","created":"2019-01-19","cited_by_count":368},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"id":"1412.8690","title":"Breaking the Curse of Dimensionality with Convex Neural Networks","created":"2014-12-30","cited_by_count":331},{"id":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1611.01491","title":"Understanding Deep Neural Networks with Rectified Linear Units","created":"2016-11-04","cited_by_count":257},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"id":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"id":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"id":"1512.03965","title":"The Power of Depth for Feedforward Neural Networks","created":"2015-12-12","cited_by_count":183},{"id":"1709.05289","title":"Optimal approximation of piecewise smooth functions using deep ReLU neural networks","created":"2017-09-15","cited_by_count":179},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1703.02391","title":"Learning from Noisy Labels with Distillation","created":"2017-03-07","cited_by_count":161},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"1611.00740","title":"Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review","created":"2016-11-02","cited_by_count":155},{"id":"1710.05468","title":"Generalization in Deep Learning","created":"2017-10-16","cited_by_count":146},{"id":"1811.08888","title":"Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks","created":"2018-11-21","cited_by_count":141},{"id":"1812.05069","title":"Recent Advances in Autoencoder-Based Representation Learning","created":"2018-12-12","cited_by_count":133},{"id":"1708.02691","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","created":"2017-08-09","cited_by_count":104},{"id":"1608.08225","title":"Why does deep and cheap learning work so well?","created":"2016-08-29","cited_by_count":100},{"id":"2001.02394","title":"Convolutional Networks with Dense Connectivity","created":"2020-01-08","cited_by_count":98},{"id":"1509.05009","title":"On the Expressive Power of Deep Learning: A Tensor Analysis","created":"2015-09-16","cited_by_count":97},{"id":"1902.07896","title":"Error bounds for approximations with deep ReLU neural networks in $W^{s,p}$ norms","created":"2019-02-21","cited_by_count":95},{"id":"1901.02220","title":"Deep Neural Network Approximation Theory","created":"2019-01-08","cited_by_count":93},{"id":"1705.01714","title":"Optimal Approximation with Sparsely Connected Deep Neural Networks","created":"2017-05-04","cited_by_count":91},{"id":"1509.08101","title":"Representation Benefits of Deep Feedforward Networks","created":"2015-09-27","cited_by_count":86},{"id":"1806.10909","title":"ResNet with one-neuron hidden layers is a Universal Approximator","created":"2018-06-28","cited_by_count":79},{"id":"1606.03813","title":"Towards an integration of deep learning and neuroscience","created":"2016-06-13","cited_by_count":78},{"id":"1904.00377","title":"A Theoretical Analysis of Deep Neural Networks and Parametric PDEs","created":"2019-03-31","cited_by_count":74},{"id":"1908.09375","title":"Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization","created":"2019-08-25","cited_by_count":72},{"id":"1912.08957","title":"Optimization for deep learning: theory and algorithms","created":"2019-12-19","cited_by_count":70},{"id":"1608.03287","title":"Deep vs. shallow networks : An approximation theory perspective","created":"2016-08-10","cited_by_count":63},{"id":"2007.01429","title":"The Global Landscape of Neural Networks: An Overview","created":"2020-07-02","cited_by_count":57},{"id":"1805.06576","title":"Mad Max: Affine Spline Insights into Deep Learning","created":"2018-05-17","cited_by_count":55},{"id":"1808.01174","title":"Generalization Error in Deep Learning","created":"2018-08-03","cited_by_count":47},{"id":"1512.06293","title":"A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction","created":"2015-12-19","cited_by_count":46},{"id":"1504.08291","title":"Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?","created":"2015-04-30","cited_by_count":41},{"id":"1705.05502","title":"The power of deeper networks for expressing natural functions","created":"2017-05-16","cited_by_count":35},{"id":"1908.00858","title":"Distilling Knowledge From a Deep Pose Regressor Network","created":"2019-08-02","cited_by_count":34},{"id":"1904.05526","title":"A Selective Overview of Deep Learning","created":"2019-04-10","cited_by_count":31},{"id":"1804.00057","title":"Understanding Autoencoders with Information Theoretic Concepts","created":"2018-03-30","cited_by_count":29},{"id":"1904.09673","title":"Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions","created":"2019-04-21","cited_by_count":29},{"id":"1506.07540","title":"Global Optimality in Tensor Factorization, Deep Learning, and Beyond","created":"2015-06-24","cited_by_count":22},{"id":"1711.06246","title":"LDMNet: Low Dimensional Manifold Regularized Neural Networks","created":"2017-11-16","cited_by_count":21},{"id":"1809.06441","title":"The physics of brain network structure, function, and control","created":"2018-09-17","cited_by_count":20},{"id":"1811.09003","title":"On a Sparse Shortcut Topology of Artificial Neural Networks","created":"2018-11-22","cited_by_count":20},{"id":"1902.07678","title":"Massive MIMO is a Reality -- What is Next? Five Promising Research Directions for Antenna Arrays","created":"2019-02-11","cited_by_count":19},{"id":"1908.01867","title":"Neuroscience-inspired online unsupervised learning algorithms","created":"2019-08-05","cited_by_count":19},{"id":"1706.00550","title":"On Unifying Deep Generative Models","created":"2017-06-02","cited_by_count":15},{"id":"1804.05012","title":"Representing smooth functions as compositions of near-identity functions with implications for deep network optimization","created":"2018-04-13","cited_by_count":15},{"id":"1811.08150","title":"Effect of Depth and Width on Local Minima in Deep Learning","created":"2018-11-20","cited_by_count":12},{"id":"1808.00408","title":"Geometry of energy landscapes and the optimizability of deep neural networks","created":"2018-08-01","cited_by_count":9},{"id":"1610.08189","title":"Tensor Decompositions for Identifying Directed Graph Topologies and Tracking Dynamic Networks","created":"2016-10-26","cited_by_count":8},{"id":"1511.06433","title":"Blending LSTMs into CNNs","created":"2015-11-19","cited_by_count":7},{"id":"2002.02515","title":"Quasi-Equivalence of Width and Depth of Neural Networks","created":"2020-02-06","cited_by_count":7},{"id":"1710.02196","title":"Porcupine Neural Networks: (Almost) All Local Optima are Global","created":"2017-10-05","cited_by_count":6},{"id":"1704.03636","title":"Energy Propagation in Deep Convolutional Neural Networks","created":"2017-04-12","cited_by_count":5},{"id":"1904.03413","title":"6G: the Wireless Communications Network for Collaborative and AI Applications","created":"2019-04-06","cited_by_count":2},{"id":"1509.05360","title":"Geometry-aware Deep Transform","created":"2015-09-17","cited_by_count":1},{"id":"1809.04711","title":"Linear Algebra and Duality of Neural Networks","created":"2018-09-12","cited_by_count":1}],"next_cursor":null}