activation function

Scaled ReLU Matters for Training Vision Transformers AAAI 2022 Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions ICLR 2022 Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique CVPR 2022 Sound and Complete Neural Network Repair with Minimality and Locality Guarantees ICLR 2022 Stochastic Adaptive Activation Function NeurIPS 2022 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NeurIPS 2022 Towards Understanding the Condensation of Neural Networks at Initial Training NeurIPS 2022 Understanding the Eluder Dimension NeurIPS 2022 Activate or Not: Learning Customized Activation CVPR 2021 Activation-level uncertainty in deep neural networks ICLR 2021 Agnostic Proper Learning of Halfspaces under Gaussian Marginals COLT 2021 Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks AAAI 2021 Deep Neural Networks as Point Estimates for Deep Gaussian Processes NeurIPS 2021 Elementary superexpressive activations ICML 2021 Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online ICLR 2021 Improving Accuracy of Binary Neural Networks Using Unbalanced Activation Distribution CVPR 2021 Learning Graph Neural Networks with Approximate Gradient Descent AAAI 2021 Learning Specialized Activation Functions With the Piecewise Linear Unit ICCV 2021 Low Curvature Activations Reduce Overfitting in Adversarial Training ICCV 2021 Non-asymptotic approximations of neural networks by Gaussian processes COLT 2021 ReAct: Out-of-distribution Detection With Rectified Activations NeurIPS 2021 Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract) AAAI 2021 Rescuing Deep Hashing from Dead Bits Problem IJCAI 2021 Revisiting Weight Initialization of Deep Neural Networks ACML 2021 Scalable Partial Explainability in Neural Networks via Flexible Activation Functions (Student Abstract) AAAI 2021