Impacts of Darwinian Evolution on Pre-trained Deep Neural Networks

• URL: http://arxiv.org/abs/2408.05563v1
• Date: Sat, 10 Aug 2024 14:08:33 GMT
• Title: Impacts of Darwinian Evolution on Pre-trained Deep Neural Networks
• Abstract summary: This work proposes a neural network optimization framework based on evolutionary theory. Experiments are carried out to examine the relationships between Darwinian evolution and neural network optimization. The proposed framework has positive impacts on the network, with reduced over-fitting and an order of magnitude lower time complexity.
• Score: 12.847052918757768
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Darwinian evolution of the biological brain is documented through multiple lines of evidence, although the modes of evolutionary changes remain unclear. Drawing inspiration from the evolved neural systems (e.g., visual cortex), deep learning models have demonstrated superior performance in visual tasks, among others. While the success of training deep neural networks has been relying on back-propagation (BP) and its variants to learn representations from data, BP does not incorporate the evolutionary processes that govern biological neural systems. This work proposes a neural network optimization framework based on evolutionary theory. Specifically, BP-trained deep neural networks for visual recognition tasks obtained from the ending epochs are considered the primordial ancestors (initial population). Subsequently, the population evolved with differential evolution. Extensive experiments are carried out to examine the relationships between Darwinian evolution and neural network optimization, including the correspondence between datasets, environment, models, and living species. The empirical results show that the proposed framework has positive impacts on the network, with reduced over-fitting and an order of magnitude lower time complexity compared to BP. Moreover, the experiments show that the proposed framework performs well on deep neural networks and big datasets.

Related papers

• Evolution imposes an inductive bias that alters and accelerates learning dynamics [49.1574468325115]
  We investigate the effect of evolutionary optimization on the learning dynamics of neural networks.<n>We combined algorithms natural selection and online learning to produce a method for evolutionarily conditioning artificial neural networks.<n>Results suggest evolution constitutes an inductive bias that tunes neural systems to enable rapid learning.
  arXiv  Detail & Related papers  (2025-05-15T18:50:57Z)
• Discovering Chunks in Neural Embeddings for Interpretability [53.80157905839065]
  We propose leveraging the principle of chunking to interpret artificial neural population activities. We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificial sequences with imposed regularities. We identify similar recurring embedding states corresponding to concepts in the input, with perturbations to these states activating or inhibiting the associated concepts.
  arXiv  Detail & Related papers  (2025-02-03T20:30:46Z)
• Emergent weight morphologies in deep neural networks [0.0]
  We show that training deep neural networks gives rise to emergent weight morphologies independent of the training data. Our work demonstrates emergence in the training of deep neural networks, which impacts the achievable performance of deep neural networks.
  arXiv  Detail & Related papers  (2025-01-09T19:48:51Z)
• Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures [7.054776300100835]
  The aim of this study is to improve the image classification performance of ANNs via a novel approach inspired by the biological nervous system architecture of planarians. The proposed planarian neural architecture-based neural network was evaluated on the CIFAR-10 and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2025-01-08T18:59:36Z)
• Contrastive Learning in Memristor-based Neuromorphic Systems [55.11642177631929]
  Spiking neural networks have become an important family of neuron-based models that sidestep many of the key limitations facing modern-day backpropagation-trained deep networks. In this work, we design and investigate a proof-of-concept instantiation of contrastive-signal-dependent plasticity (CSDP), a neuromorphic form of forward-forward-based, backpropagation-free learning.
  arXiv  Detail & Related papers  (2024-09-17T04:48:45Z)
• Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields [56.69755544814834]
  We present evidence suggesting that depthwise convolutional kernels are effectively replicating the biological receptive fields observed in the mammalian retina. We propose a scheme that draws inspiration from the biological receptive fields.
  arXiv  Detail & Related papers  (2024-01-18T18:06:22Z)
• Dive into the Power of Neuronal Heterogeneity [8.6837371869842]
  We show the challenges faced by backpropagation-based methods in optimizing Spiking Neural Networks (SNNs) and achieve more robust optimization of heterogeneous neurons in random networks using an Evolutionary Strategy (ES) We find that membrane time constants play a crucial role in neural heterogeneity, and their distribution is similar to that observed in biological experiments.
  arXiv  Detail & Related papers  (2023-05-19T07:32:29Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustness [15.29595828816055]
  This work proposes MO-EvoPruneDeepTL, a multi-objective evolutionary pruning algorithm. We use Transfer Learning to adapt the last layers of Deep Neural Networks, by replacing them with sparse layers evolved by a genetic algorithm. Experiments show that our proposal achieves promising results in all the objectives, and direct relation are presented.
  arXiv  Detail & Related papers  (2023-02-20T19:33:38Z)
• Sparse Mutation Decompositions: Fine Tuning Deep Neural Networks with Subspace Evolution [0.0]
  A popular subclass of neuroevolutionary methods, called evolution strategies, relies on dense noise perturbations to mutate networks. We introduce an approach to alleviating this problem by decomposing dense mutations into low-dimensional subspaces. We conduct the first large scale exploration of neuroevolutionary fine tuning and ensembling on the notoriously difficult ImageNet dataset.
  arXiv  Detail & Related papers  (2023-02-12T01:27:26Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution [22.058311878382142]
  This study explores the relationship between convolutional neural networks and finite Volterra convolutions. It provides a novel approach to explain and study the overall characteristics of neural networks without being disturbed by the complex network architectures.
  arXiv  Detail & Related papers  (2021-10-19T12:07:46Z)
• Epigenetic evolution of deep convolutional models [81.21462458089142]
  We build upon a previously proposed neuroevolution framework to evolve deep convolutional models. We propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator.
  arXiv  Detail & Related papers  (2021-04-12T12:45:16Z)
• The Neural Coding Framework for Learning Generative Models [91.0357317238509]
  We propose a novel neural generative model inspired by the theory of predictive processing in the brain. In a similar way, artificial neurons in our generative model predict what neighboring neurons will do, and adjust their parameters based on how well the predictions matched reality.
  arXiv  Detail & Related papers  (2020-12-07T01:20:38Z)

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.