{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2012.09265","title":"Variational Quantum Algorithms","created":"2020-12-16","cited_by_count":692},{"id":"1803.11173","title":"Barren plateaus in quantum neural network training landscapes","created":"2018-03-29","cited_by_count":630},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"1902.10445","title":"Efficient Learning for Deep Quantum Neural Networks","created":"2019-02-27","cited_by_count":161},{"id":"1806.02375","title":"Understanding Batch Normalization","created":"2018-06-01","cited_by_count":159},{"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":"1911.12207","title":"Orthogonal Convolutional Neural Networks","created":"2019-11-27","cited_by_count":123},{"id":"1902.09689","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","created":"2019-02-26","cited_by_count":112},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105},{"id":"1511.06067","title":"Convolutional neural networks with low-rank regularization","created":"2015-11-19","cited_by_count":103},{"id":"1805.10408","title":"The Singular Values of Convolutional Layers","created":"2018-05-26","cited_by_count":95},{"id":"1611.00035","title":"Full-Capacity Unitary Recurrent Neural Networks","created":"2016-10-31","cited_by_count":94},{"id":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"2006.12070","title":"Lipschitz Recurrent Neural Networks","created":"2020-06-22","cited_by_count":89},{"id":"1911.00937","title":"Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks","created":"2019-11-03","cited_by_count":87},{"id":"1707.09520","title":"Orthogonal Recurrent Neural Networks with Scaled Cayley Transform","created":"2017-07-29","cited_by_count":83},{"id":"2002.01113","title":"Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform","created":"2020-02-04","cited_by_count":80},{"id":"1806.06871","title":"Continuous-variable quantum neural networks","created":"2018-06-18","cited_by_count":74},{"id":"1402.3511","title":"A Clockwork RNN","created":"2014-02-14","cited_by_count":72},{"id":"1905.05929","title":"Orthogonal Deep Neural Networks","created":"2019-05-15","cited_by_count":72},{"id":"2105.11417","title":"Skew Orthogonal Convolutions","created":"2021-05-24","cited_by_count":67},{"id":"1612.05231","title":"Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs","created":"2016-12-15","cited_by_count":65},{"id":"1810.09102","title":"Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?","created":"2018-10-22","cited_by_count":62},{"id":"1612.00188","title":"Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections","created":"2016-12-01","cited_by_count":57},{"id":"2004.04690","title":"Orthogonal Over-Parameterized Training","created":"2020-04-09","cited_by_count":44},{"id":"1802.05779","title":"Quantum Variational Autoencoder","created":"2018-02-15","cited_by_count":41},{"id":"1602.06662","title":"Recurrent Orthogonal Networks and Long-Memory Tasks","created":"2016-02-22","cited_by_count":38},{"id":"2006.02427","title":"Lyapunov spectra of chaotic recurrent neural networks","created":"2020-06-03","cited_by_count":37},{"id":"2004.00917","title":"Controllable Orthogonalization in Training DNNs","created":"2020-04-02","cited_by_count":30},{"id":"1408.2873","title":"First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs","created":"2014-08-12","cited_by_count":28},{"id":"2001.00550","title":"Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits","created":"2020-01-02","cited_by_count":26},{"id":"1511.06744","title":"Training CNNs with Low-Rank Filters for Efficient Image Classification","created":"2015-11-20","cited_by_count":25},{"id":"2001.11897","title":"Learning Unitaries by Gradient Descent","created":"2020-01-31","cited_by_count":20},{"id":"2110.06084","title":"Implicit Bias of Linear Equivariant Networks","created":"2021-10-12","cited_by_count":19},{"id":"1905.10415","title":"Quantum-inspired algorithms in practice","created":"2019-05-24","cited_by_count":18},{"id":"2006.01910","title":"The Convolution Exponential and Generalized Sylvester Flows","created":"2020-06-02","cited_by_count":18},{"id":"1607.04903","title":"Learning Unitary Operators with Help From u(n)","created":"2016-07-17","cited_by_count":15},{"id":"1504.01575","title":"Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series","created":"2015-04-07","cited_by_count":14},{"id":"1812.03089","title":"Quantum algorithms for feedforward neural networks","created":"2018-12-07","cited_by_count":14},{"id":"1905.05796","title":"Approximating Orthogonal Matrices with Effective Givens Factorization","created":"2019-05-14","cited_by_count":7},{"id":"2109.11330","title":"Quantum algorithms for group convolution, cross-correlation, and equivariant transformations","created":"2021-09-23","cited_by_count":5}],"next_cursor":null}