Task-Specific Activation Functions for Neuroevolution using Grammatical Evolution

• URL: http://arxiv.org/abs/2503.10879v2
• Date: Wed, 26 Mar 2025 17:39:57 GMT
• Title: Task-Specific Activation Functions for Neuroevolution using Grammatical Evolution
• Authors: Benjamin David Winter, William John Teahan,
• Abstract summary: We introduce Neuvo GEAF - an innovative approach leveraging grammatical evolution (GE) to automatically evolve novel activation functions.<n>Experiments conducted on well-known binary classification datasets show statistically significant improvements in F1-score (between 2.4% and 9.4%) over ReLU.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Activation functions play a critical role in the performance and behaviour of neural networks, significantly impacting their ability to learn and generalise. Traditional activation functions, such as ReLU, sigmoid, and tanh, have been widely used with considerable success. However, these functions may not always provide optimal performance for all tasks and datasets. In this paper, we introduce Neuvo GEAF - an innovative approach leveraging grammatical evolution (GE) to automatically evolve novel activation functions tailored to specific neural network architectures and datasets. Experiments conducted on well-known binary classification datasets show statistically significant improvements in F1-score (between 2.4% and 9.4%) over ReLU using identical network architectures. Notably, these performance gains were achieved without increasing the network's parameter count, supporting the trend toward more efficient neural networks that can operate effectively on resource-constrained edge devices. This paper's findings suggest that evolved activation functions can provide significant performance improvements for compact networks while maintaining energy efficiency during both training and inference phases.

Related papers

• Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization [66.03821840425539]
  In this paper, we investigate the training dynamics of $L$-layer neural networks using the tensor gradient program (SGD) framework.<n>We show that SGD enables these networks to learn linearly independent features that substantially deviate from their initial values.<n>This rich feature space captures relevant data information and ensures that any convergent point of the training process is a global minimum.
  arXiv  Detail & Related papers  (2025-03-12T17:33:13Z)
• LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation [64.34935748707673]
  Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. We propose a novel method of Learning Resampling (termed LeRF) which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption. LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the shapes of these resampling functions with a neural network.
  arXiv  Detail & Related papers  (2024-07-13T16:09:45Z)
• APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks [0.0]
  We introduce a novel trainable activation function, adaptive piecewise approximated activation linear unit (APALU) Experiments reveal significant improvements over widely used activation functions for different tasks. APALU achieves 100% accuracy on a sign language recognition task with a limited dataset.
  arXiv  Detail & Related papers  (2024-02-13T06:18:42Z)
• EMN: Brain-inspired Elastic Memory Network for Quick Domain Adaptive Feature Mapping [57.197694698750404]
  We propose a novel gradient-free Elastic Memory Network to support quick fine-tuning of the mapping between features and prediction. EMN adopts randomly connected neurons to memorize the association of features and labels, where the signals in the network are propagated as impulses. EMN can achieve up to 10% enhancement of performance while only needing less than 1% timing cost of traditional domain adaptation methods.
  arXiv  Detail & Related papers  (2024-02-04T09:58:17Z)
• Efficient Activation Function Optimization through Surrogate Modeling [15.219959721479835]
  This paper aims to improve the state of the art through three steps. First, the benchmark Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT were created by training convolutional, residual, and vision transformer architectures. Second, a characterization of the benchmark space was developed, leading to a new surrogate-based method for optimization.
  arXiv  Detail & Related papers  (2023-01-13T23:11:14Z)
• Transformers with Learnable Activation Functions [63.98696070245065]
  We use Rational Activation Function (RAF) to learn optimal activation functions during training according to input data. RAF opens a new research direction for analyzing and interpreting pre-trained models according to the learned activation functions.
  arXiv  Detail & Related papers  (2022-08-30T09:47:31Z)
• Efficient Feature Transformations for Discriminative and Generative Continual Learning [98.10425163678082]
  We propose a simple task-specific feature map transformation strategy for continual learning. Theses provide powerful flexibility for learning new tasks, achieved with minimal parameters added to the base architecture. We demonstrate the efficacy and efficiency of our method with an extensive set of experiments in discriminative (CIFAR-100 and ImageNet-1K) and generative sequences of tasks.
  arXiv  Detail & Related papers  (2021-03-25T01:48:14Z)
• Discovering Parametric Activation Functions [17.369163074697475]
  This paper proposes a technique for customizing activation functions automatically, resulting in reliable improvements in performance. Experiments with four different neural network architectures on the CIFAR-10 and CIFAR-100 image classification datasets show that this approach is effective.
  arXiv  Detail & Related papers  (2020-06-05T00:25:33Z)
• Evolutionary Optimization of Deep Learning Activation Functions [15.628118691027328]
  We show that evolutionary algorithms can discover novel activation functions that outperform the Rectified Linear Unit (ReLU) replacing ReLU with evolved activation functions results in statistically significant increases in network accuracy. These novel activation functions are shown to generalize, achieving high performance across tasks.
  arXiv  Detail & Related papers  (2020-02-17T19:54:26Z)
• Cooperative Initialization based Deep Neural Network Training [35.14235994478142]
  Our approach uses multiple activation functions in the initial few epochs for the update of all sets of weight parameters while training the network. Our approach outperforms various baselines and, at the same time, performs well over various tasks such as classification and detection.
  arXiv  Detail & Related papers  (2020-01-05T14:08:46Z)
• Alpha Discovery Neural Network based on Prior Knowledge [55.65102700986668]
  Genetic programming (GP) is the state-of-the-art in financial automated feature construction task. This paper proposes Alpha Discovery Neural Network (ADNN), a tailored neural network structure which can automatically construct diversified financial technical indicators.
  arXiv  Detail & Related papers  (2019-12-26T03:10:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.