{"list":"other","total":58,"rows":[{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1906.01563","title":"Hamiltonian Neural Networks","created":"2019-06-04","cited_by_count":712},{"id":"2005.08926","title":"Neural Controlled Differential Equations for Irregular Time Series","created":"2020-05-18","cited_by_count":506},{"id":"1705.03341","title":"Stable Architectures for Deep Neural Networks","created":"2017-05-09","cited_by_count":341},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"1907.04490","title":"Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning","created":"2019-07-10","cited_by_count":212},{"id":"1710.10121","title":"Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations","created":"2017-10-27","cited_by_count":203},{"id":"1409.2329","title":"Recurrent Neural Network Regularization","created":"2014-09-08","cited_by_count":189},{"id":"1909.12077","title":"Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control","created":"2019-09-26","cited_by_count":184},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"1905.09883","title":"Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit","created":"2019-05-23","cited_by_count":176},{"id":"1812.00740","title":"Disentangling Adversarial Robustness and Generalization","created":"2018-12-03","cited_by_count":172},{"id":"1710.04340","title":"Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition","created":"2017-10-12","cited_by_count":158},{"id":"1909.13334","title":"Symplectic Recurrent Neural Networks","created":"2019-09-29","cited_by_count":150},{"id":"1909.13789","title":"Hamiltonian Generative Networks","created":"2019-09-30","cited_by_count":137},{"id":"1901.08428","title":"Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group","created":"2019-01-24","cited_by_count":134},{"id":"1504.00941","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","created":"2015-04-03","cited_by_count":130},{"id":"1605.08254","title":"Robust Large Margin Deep Neural Networks","created":"2016-05-26","cited_by_count":118},{"id":"1605.07571","title":"Sequential Neural Models with Stochastic Layers","created":"2016-05-24","cited_by_count":115},{"id":"2003.02236","title":"Forecasting Sequential Data using Consistent Koopman Autoencoders","created":"2020-03-04","cited_by_count":115},{"id":"1902.09689","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","created":"2019-02-26","cited_by_count":112},{"id":"2009.10713","title":"Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't","created":"2020-09-22","cited_by_count":95},{"id":"2006.12070","title":"Lipschitz Recurrent Neural Networks","created":"2020-06-22","cited_by_count":89},{"id":"1802.08241","title":"Hessian-based Analysis of Large Batch Training and Robustness to Adversaries","created":"2018-02-22","cited_by_count":87},{"id":"2010.00951","title":"Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","created":"2020-10-02","cited_by_count":82},{"id":"1905.03684","title":"Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation","created":"2019-05-09","cited_by_count":71},{"id":"2002.12915","title":"The Implicit and Explicit Regularization Effects of Dropout","created":"2020-02-28","cited_by_count":71},{"id":"1905.10866","title":"Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction","created":"2019-05-26","cited_by_count":67},{"id":"1910.08264","title":"Learning Compositional Koopman Operators for Model-Based Control","created":"2019-10-18","cited_by_count":67},{"id":"1805.10369","title":"Stable Recurrent Models","created":"2018-05-25","cited_by_count":66},{"id":"2003.07802","title":"The Implicit Regularization of Stochastic Gradient Flow for Least Squares","created":"2020-03-17","cited_by_count":59},{"id":"1710.05179","title":"Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization","created":"2017-10-14","cited_by_count":56},{"id":"1906.03663","title":"Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability","created":"2019-06-09","cited_by_count":53},{"id":"1912.12777","title":"Machine Learning from a Continuous Viewpoint","created":"2019-12-30","cited_by_count":50},{"id":"2006.03860","title":"Do RNN and LSTM have Long Memory?","created":"2020-06-06","cited_by_count":47},{"id":"1806.05394","title":"Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks","created":"2018-06-14","cited_by_count":45},{"id":"2008.02389","title":"Continuous-in-Depth Neural Networks","created":"2020-08-05","cited_by_count":40},{"id":"2006.02427","title":"Lyapunov spectra of chaotic recurrent neural networks","created":"2020-06-03","cited_by_count":37},{"id":"2007.07368","title":"Explicit Regularisation in Gaussian Noise Injections","created":"2020-07-14","cited_by_count":37},{"id":"1912.04533","title":"Exact expressions for double descent and implicit regularization via surrogate random design","created":"2019-12-10","cited_by_count":35},{"id":"2006.02361","title":"Optimizing Neural Networks via Koopman Operator Theory","created":"2020-06-03","cited_by_count":33},{"id":"1801.00173","title":"Theory of Deep Learning III: explaining the non-overfitting puzzle","created":"2017-12-30","cited_by_count":32},{"id":"2006.14123","title":"On Lyapunov Exponents for RNNs: Understanding Information Propagation Using Dynamical Systems Tools","created":"2020-06-25","cited_by_count":31},{"id":"2003.03397","title":"Dropout: Explicit Forms and Capacity Control","created":"2020-03-06","cited_by_count":27},{"id":"1902.09742","title":"Deep Variational Koopman Models: Inferring Koopman Observations for Uncertainty-Aware Dynamics Modeling and Control","created":"2019-02-26","cited_by_count":18},{"id":"1912.13053","title":"Disentangling Trainability and Generalization in Deep Neural Networks","created":"2019-12-30","cited_by_count":16},{"id":"1902.10887","title":"Towards Robust ResNet: A Small Step but A Giant Leap","created":"2019-02-28","cited_by_count":15},{"id":"1511.03771","title":"Improving performance of recurrent neural network with relu nonlinearity","created":"2015-11-12","cited_by_count":12},{"id":"1812.00174","title":"Stochastic Training of Residual Networks: a Differential Equation Viewpoint","created":"2018-12-01","cited_by_count":12},{"id":"2101.07833","title":"Implicit Bias of Linear RNNs","created":"2021-01-19","cited_by_count":11},{"id":"2006.11052","title":"Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory","created":"2020-06-19","cited_by_count":10},{"id":"1805.01500","title":"Noisin: Unbiased Regularization for Recurrent Neural Networks","created":"2018-05-03","cited_by_count":8},{"id":"1911.10305","title":"Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families","created":"2019-11-23","cited_by_count":5},{"id":"2006.05547","title":"Deep Adversarial Koopman Model for Reaction-Diffusion systems","created":"2020-06-09","cited_by_count":3}],"next_cursor":null}