← Optimization & Theory
Deep Learning › Optimization & Theory ›

Neural Network Optimization

902 directly classified papers

Papers per year

Papers

Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks AAAI 2020
Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference AAAI 2020
DARB: A Density-Adaptive Regular-Block Pruning for Deep Neural Networks AAAI 2020
Lipschitz Constrained Parameter Initialization for Deep Transformers ACL 2020
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change ACL 2020
Biologically Inspired Sleep Algorithm for Reducing Catastrophic Forgetting in Neural Networks AAAI 2020
PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-Time Execution on Mobile Devices AAAI 2020
The HSIC Bottleneck: Deep Learning without Back-Propagation AAAI 2020
Understanding the Disharmony between Weight Normalization Family and Weight Decay AAAI 2020
Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks AAAI 2020
DIANet: Dense-and-Implicit Attention Network AAAI 2020
Eigenvalue Normalized Recurrent Neural Networks for Short Term Memory AAAI 2020
Adaptive Convolutional ReLUs AAAI 2020
NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks CVPR 2020
SGAS: Sequential Greedy Architecture Search CVPR 2020
ReSprop: Reuse Sparsified Backpropagation CVPR 2020
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing CVPR 2020
Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation CVPR 2020
Continual Learning With Extended Kronecker-Factored Approximate Curvature CVPR 2020
Cogradient Descent for Bilinear Optimization CVPR 2020
F-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation CVPR 2020
Learning Dynamic Routing for Semantic Segmentation CVPR 2020
Learning to Optimize Non-Rigid Tracking CVPR 2020
Filter Grafting for Deep Neural Networks CVPR 2020
An Investigation Into the Stochasticity of Batch Whitening CVPR 2020