activation function

Tanh Works Better with Asymmetry NeurIPS 2023 The k-Cap Process on Geometric Random Graphs COLT 2023 Understanding the Inner-workings of Language Models Through Representation Dissimilarity EMNLP 2023 Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning ICLR 2023 Unraveling Feature Extraction Mechanisms in Neural Networks EMNLP 2023 VRA: Variational Rectified Activation for Out-of-distribution Detection NeurIPS 2023 Why do networks have inhibitory/negative connections? ICCV 2023 Adaptable Adapters NAACL 2022 A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions AISTATS 2022 A spectral-based analysis of the separation between two-layer neural networks and linear methods JMLR 2022 Automatically Gating Multi-Frequency Patterns through Rectified Continuous Bernoulli Units with Theoretical Principles IJCAI 2022 Coin Flipping Neural Networks ICML 2022 Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers ICLR 2022 Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons JMLR 2022 Depth separation beyond radial functions JMLR 2022 DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks ICML 2022 ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions AAAI 2022 Fractional Adaptive Linear Units AAAI 2022 Gardner formula for Ising perceptron models at small densities COLT 2022 Generalization Properties of NAS under Activation and Skip Connection Search NeurIPS 2022 Learning a Single Neuron for Non-monotonic Activation Functions AISTATS 2022 Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators NeurIPS 2022 Most Activation Functions Can Win the Lottery Without Excessive Depth NeurIPS 2022 Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks ICLR 2022 Reverse Engineering the Neural Tangent Kernel ICML 2022