{"total":32,"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":"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":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2205.09459","title":"Neural Network Architecture Beyond Width and Depth","created":"2022-05-19","cited_by_count":17,"area":null},{"id":"2101.09957","title":"Activation Functions in Artificial Neural Networks: A Systematic Overview","created":"2021-01-25","cited_by_count":13,"area":null},{"id":"2105.07741","title":"Activation function design for deep networks: linearity and effective initialisation","created":"2021-05-17","cited_by_count":13,"area":null},{"id":"2410.23451","title":"Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints","created":"2024-10-30","cited_by_count":9,"area":null},{"id":"2103.17059","title":"Reliable Detection of Compressed and Encrypted Data","created":"2021-03-31","cited_by_count":8,"area":null},{"id":"2311.03733","title":"Improved weight initialization for deep and narrow feedforward neural network","created":"2023-11-07","cited_by_count":7,"area":null},{"id":"2403.07688","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2407.07564","title":"Trainable Highly-expressive Activation Functions","created":"2024-07-10","cited_by_count":6,"area":null},{"id":"2210.01607","title":"A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaeras","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2409.10463","title":"Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptrons","created":"2024-09-16","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":"2112.11846","title":"A Discriminative Single-Shot Segmentation Network for Visual Object Tracking","created":"2021-12-22","cited_by_count":4,"area":null},{"id":"2103.06583","title":"Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks","created":"2021-03-11","cited_by_count":3,"area":null},{"id":"2112.09442","title":"Adaptively Customizing Activation Functions for Various Layers","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2209.08735","title":"Traffic incident duration prediction via a deep learning framework for text description encoding","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2402.08244","title":"APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2505.09486","title":"Preserving Plasticity in Continual Learning with Adaptive Linearity Injection","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2103.12499","title":"Initializing ReLU networks in an expressive subspace of weights","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2108.00700","title":"Piecewise Linear Units Improve Deep Neural Networks","created":"2021-08-02","cited_by_count":1,"area":null},{"id":"2201.01384","title":"Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network","created":"2022-01-04","cited_by_count":1,"area":null},{"id":"2402.09249","title":"Exploring the Relationship: Transformative Adaptive Activation Functions in Comparison to Other Activation Functions","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2408.06820","title":"Efficient Search for Customized Activation Functions with Gradient Descent","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2503.21166","title":"Unveiling the Potential of Superexpressive Networks in Implicit Neural Representations","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2111.14349","title":"First Power Linear Unit with Sign","created":"2021-11-29","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":"2309.17194","title":"Generalized Activation via Multivariate Projection","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2405.03712","title":"Your Network May Need to Be Rewritten: Network Adversarial Based on High-Dimensional Function Graph Decomposition","created":"2024-05-04","cited_by_count":0,"area":null},{"id":"2508.00135","title":"Exploring the Feasibility of Deep Learning Techniques for Accurate Gender Classification from Eye Images","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.05073","title":"ULU: A Unified Activation Function","created":"2025-08-07","cited_by_count":0,"area":null}],"next_cursor":null}