{"total":53,"rows":[{"id":"2109.14545","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","created":"2021-09-29","cited_by_count":155,"area":null},{"id":"2105.09513","title":"Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions","created":"2021-05-20","cited_by_count":49,"area":null},{"id":"2209.02681","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","created":"2022-09-06","cited_by_count":29,"area":null},{"id":"2110.02180","title":"Noisy Feature Mixup","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2207.02099","title":"An Empirical Study of Implicit Regularization in Deep Offline RL","created":"2022-07-05","cited_by_count":24,"area":"offlinerl"},{"id":"2112.04036","title":"DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs","created":"2021-12-07","cited_by_count":19,"area":null},{"id":"2401.00955","title":"Learning Long Sequences in Spiking Neural Networks","created":"2023-12-14","cited_by_count":19,"area":null},{"id":"2102.07379","title":"On the Inherent Regularization Effects of Noise Injection During Training","created":"2021-02-15","cited_by_count":18,"area":null},{"id":"2202.01263","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","created":"2022-02-02","cited_by_count":17,"area":null},{"id":"2210.04349","title":"Nonlinear Sufficient Dimension Reduction with a Stochastic Neural Network","created":"2022-10-09","cited_by_count":10,"area":null},{"id":"2302.00061","title":"Dynamic Flows on Curved Space Generated by Labeled Data","created":"2023-01-31","cited_by_count":10,"area":null},{"id":"2201.05319","title":"A Kernel-Expanded Stochastic Neural Network","created":"2022-01-14","cited_by_count":9,"area":null},{"id":"2307.14611","title":"TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2102.04450","title":"Noise Optimization for Artificial Neural Networks","created":"2021-02-06","cited_by_count":7,"area":null},{"id":"2504.00233","title":"Over-the-Air Edge Inference via End-to-End Metasurfaces-Integrated Artificial Neural Networks","created":"2025-03-31","cited_by_count":7,"area":null},{"id":"2301.09245","title":"Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks","created":"2023-01-23","cited_by_count":6,"area":null},{"id":"2201.11624","title":"LiteLSTM Architecture for Deep Recurrent Neural Networks","created":"2022-01-27","cited_by_count":5,"area":null},{"id":"2204.12589","title":"Self-scalable Tanh (Stan): Faster Convergence and Better Generalization in Physics-informed Neural Networks","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2302.12304","title":"Uncertainty Injection: A Deep Learning Method for Robust Optimization","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2503.09206","title":"Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients","created":"2025-03-12","cited_by_count":5,"area":null},{"id":"2508.03965","title":"BubbleOKAN: A Physics-Informed Interpretable Neural Operator for High-Frequency Bubble Dynamics","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2111.13858","title":"Why KDAC? A general activation function for knowledge discovery","created":"2021-11-27","cited_by_count":4,"area":null},{"id":"2206.12166","title":"Neural Networks with A La Carte Selection of Activation Functions","created":"2022-06-24","cited_by_count":4,"area":null},{"id":"2211.10828","title":"Instability in clinical risk stratification models using deep learning","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2305.15835","title":"PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2102.02315","title":"Real-Time Optimal Trajectory Planning for Autonomous Vehicles and Lap Time Simulation Using Machine Learning","created":"2021-02-03","cited_by_count":2,"area":null},{"id":"2110.12197","title":"Towards a Robust Differentiable Architecture Search under Label Noise","created":"2021-10-23","cited_by_count":2,"area":null},{"id":"2212.12018","title":"Langevin algorithms for Markovian Neural Networks and Deep Stochastic control","created":"2022-12-22","cited_by_count":2,"area":null},{"id":"2404.03992","title":"Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks","created":"2024-04-05","cited_by_count":2,"area":null},{"id":"2503.16183","title":"Variance-Aware Noisy Training: Hardening DNNs against Unstable Analog Computations","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2206.05643","title":"Density Regression and Uncertainty Quantification with Bayesian Deep Noise Neural Networks","created":"2022-06-12","cited_by_count":1,"area":null},{"id":"2208.11873","title":"Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2212.14718","title":"Langevin algorithms for very deep Neural Networks with application to image classification","created":"2022-12-27","cited_by_count":1,"area":null},{"id":"2301.04794","title":"LiteLSTM Architecture Based on Weights Sharing for Recurrent Neural Networks","created":"2023-01-12","cited_by_count":1,"area":null},{"id":"2307.09463","title":"A Cryogenic Memristive Neural Decoder for Fault-tolerant Quantum Error Correction","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2405.02564","title":"Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks","created":"2024-05-04","cited_by_count":1,"area":null},{"id":"2409.04915","title":"Activation Function Optimization Scheme for Image Classification","created":"2024-09-07","cited_by_count":1,"area":null},{"id":"2507.22089","title":"Principled Curriculum Learning using Parameter Continuation Methods","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2605.17659","title":"Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2104.01478","title":"\"Forget\" the Forget Gate: Estimating Anomalies in Videos using Self-contained Long Short-Term Memory Networks","created":"2021-04-03","cited_by_count":0,"area":null},{"id":"2107.14582","title":"NeuralDP Differentially private neural networks by design","created":"2021-07-30","cited_by_count":0,"area":null},{"id":"2110.12246","title":"Parametric Variational Linear Units (PVLUs) in Deep Convolutional Networks","created":"2021-10-23","cited_by_count":0,"area":null},{"id":"2111.14349","title":"First Power Linear Unit with Sign","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2210.01348","title":"Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2302.11007","title":"Unification of popular artificial neural network activation functions","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2304.04455","title":"Bayesian optimization for sparse neural networks with trainable activation functions","created":"2023-04-10","cited_by_count":0,"area":null},{"id":"2411.15191","title":"Finding One's Bearings in the Hyperparameter Landscape of a Wide-Kernel Convolutional Fault Detector","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2503.22810","title":"Harnessing uncertainty when learning through Equilibrium Propagation in neural networks","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2507.11493","title":"A parametric activation function based on Wendland RBF","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2511.07559","title":"N-ReLU: Zero-Mean Stochastic Extension of ReLU","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2511.19364","title":"Neural surrogates for designing gravitational wave detectors","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.20533","title":"Over-the-Air Goal-Oriented Communications","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2601.16446","title":"Brownian ReLU(Br-ReLU): A New Activation Function for a Long-Short Term Memory (LSTM) Network","created":"2026-01-23","cited_by_count":0,"area":null}],"next_cursor":null}