{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1705.07057","title":"Masked Autoregressive Flow for Density Estimation","created":"2017-05-19","cited_by_count":684},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"1703.01961","title":"Multiplicative Normalizing Flows for Variational Bayesian Neural Networks","created":"2017-03-06","cited_by_count":157},{"id":"1803.04831","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","created":"2018-03-13","cited_by_count":143},{"id":"2001.07416","title":"Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities","created":"2020-01-21","cited_by_count":126},{"id":"1610.03483","title":"Learning in Implicit Generative Models","created":"2016-10-11","cited_by_count":125},{"id":"1512.07666","title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","created":"2015-12-23","cited_by_count":121},{"id":"1711.00123","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","created":"2017-10-31","cited_by_count":106},{"id":"1610.09513","title":"Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences","created":"2016-10-29","cited_by_count":99},{"id":"1511.02386","title":"Hierarchical Variational Models","created":"2015-11-07","cited_by_count":89},{"id":"1703.07370","title":"REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models","created":"2017-03-21","cited_by_count":79},{"id":"1602.05473","title":"Auxiliary Deep Generative Models","created":"2016-02-17","cited_by_count":72},{"id":"1805.11183","title":"Semi-Implicit Variational Inference","created":"2018-05-28","cited_by_count":55},{"id":"1906.02914","title":"Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations","created":"2019-06-07","cited_by_count":51},{"id":"1708.06834","title":"Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks","created":"2017-08-22","cited_by_count":49},{"id":"1609.06354","title":"Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatches","created":"2016-09-20","cited_by_count":42},{"id":"1611.09630","title":"Improving Variational Auto-Encoders using Householder Flow","created":"2016-11-29","cited_by_count":42},{"id":"1709.02536","title":"Covariances, Robustness, and Variational Bayes","created":"2017-09-08","cited_by_count":40},{"id":"1611.06585","title":"Variational Boosting: Iteratively Refining Posterior Approximations","created":"2016-11-20","cited_by_count":37},{"id":"1808.02078","title":"Unbiased Implicit Variational Inference","created":"2018-08-06","cited_by_count":33},{"id":"1511.06499","title":"The Variational Gaussian Process","created":"2015-11-20","cited_by_count":30},{"id":"1810.11764","title":"Learning Sparse Neural Networks via Sensitivity-Driven Regularization","created":"2018-10-28","cited_by_count":26},{"id":"1611.05559","title":"Boosting Variational Inference","created":"2016-11-17","cited_by_count":22},{"id":"1810.02789","title":"Doubly Semi-Implicit Variational Inference","created":"2018-10-05","cited_by_count":19},{"id":"1506.04088","title":"Linear Response Methods for Accurate Covariance Estimates from Mean Field Variational Bayes","created":"2015-06-12","cited_by_count":14},{"id":"2002.05155","title":"Learnable Bernoulli Dropout for Bayesian Deep Learning","created":"2020-02-12","cited_by_count":14},{"id":"1506.05860","title":"Variational Gaussian Copula Inference","created":"2015-06-19","cited_by_count":12},{"id":"2101.06070","title":"Efficient Semi-Implicit Variational Inference","created":"2021-01-15","cited_by_count":9},{"id":"2006.06646","title":"NADS: Neural Architecture Distribution Search for Uncertainty Awareness","created":"2020-06-11","cited_by_count":8},{"id":"1706.02326","title":"Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow","created":"2017-06-07","cited_by_count":3},{"id":"1807.11143","title":"ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary Networks","created":"2018-07-30","cited_by_count":3},{"id":"1902.05696","title":"Learning to Adaptively Scale Recurrent Neural Networks","created":"2019-02-15","cited_by_count":3},{"id":"1901.02427","title":"Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models","created":"2019-01-08","cited_by_count":2},{"id":"1302.1616","title":"Sensor Selection Based on Generalized Information Gain for Target Tracking in Large Sensor Networks","created":"2013-02-06","cited_by_count":1},{"id":"1505.06169","title":"Learning Dynamic Feature Selection for Fast Sequential Prediction","created":"2015-05-22","cited_by_count":1}],"next_cursor":null}