{"list":"other","total":55,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1702.01135","title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks","created":"2017-02-03","cited_by_count":744},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1711.00851","title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","created":"2017-11-02","cited_by_count":567},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"1408.5093","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","created":"2014-06-20","cited_by_count":288},{"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":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"1512.01274","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","created":"2015-12-03","cited_by_count":195},{"id":"1302.4389","title":"Maxout Networks","created":"2013-02-18","cited_by_count":187},{"id":"1901.09021","title":"Complexity of Linear Regions in Deep Networks","created":"2019-01-25","cited_by_count":167},{"id":"1711.02114","title":"Bounding and Counting Linear Regions of Deep Neural Networks","created":"2017-11-06","cited_by_count":161},{"id":"1611.04231","title":"Identity Matters in Deep Learning","created":"2016-11-14","cited_by_count":109},{"id":"1705.01040","title":"Maximum Resilience of Artificial Neural Networks","created":"2017-04-28","cited_by_count":97},{"id":"1312.6098","title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","created":"2013-12-20","cited_by_count":94},{"id":"1905.00078","title":"Deep Learning for Audio Signal Processing","created":"2019-04-30","cited_by_count":92},{"id":"1603.05201","title":"Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units","created":"2016-03-16","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":"1704.08045","title":"The loss surface of deep and wide neural networks","created":"2017-04-26","cited_by_count":74},{"id":"1412.6830","title":"Learning Activation Functions to Improve Deep Neural Networks","created":"2014-12-21","cited_by_count":63},{"id":"1912.09899","title":"Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing","created":"2019-12-20","cited_by_count":54},{"id":"2006.00978","title":"On the Number of Linear Regions of Convolutional Neural Networks","created":"2020-06-01","cited_by_count":49},{"id":"2102.04373","title":"Partition-based formulations for mixed-integer optimization of trained ReLU neural networks","created":"2021-02-08","cited_by_count":39},{"id":"2109.05422","title":"Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?","created":"2021-09-12","cited_by_count":38},{"id":"1603.00162","title":"Convolutional Rectifier Networks as Generalized Tensor Decompositions","created":"2016-03-01","cited_by_count":32},{"id":"1707.02444","title":"Global optimality conditions for deep neural networks","created":"2017-07-08","cited_by_count":31},{"id":"1802.03487","title":"Small nonlinearities in activation functions create bad local minima in neural networks","created":"2018-02-10","cited_by_count":28},{"id":"1802.03713","title":"$\\mathcal{G}$-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space","created":"2018-02-11","cited_by_count":27},{"id":"1512.07030","title":"Deep Learning with S-shaped Rectified Linear Activation Units","created":"2015-12-22","cited_by_count":26},{"id":"2110.05518","title":"Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs","created":"2021-10-11","cited_by_count":25},{"id":"1808.04685","title":"Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization","created":"2018-08-14","cited_by_count":21},{"id":"1905.11428","title":"Equivalent and Approximate Transformations of Deep Neural Networks","created":"2019-05-27","cited_by_count":11},{"id":"1605.07154","title":"Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations","created":"2016-05-23","cited_by_count":4},{"id":"1905.06518","title":"Efficient hinging hyperplanes neural network and its application in nonlinear system identification","created":"2019-05-15","cited_by_count":4},{"id":"2103.06189","title":"Piecewise linear regression and classification","created":"2021-03-10","cited_by_count":2}],"next_cursor":null}