Optimizing Deep Neural Networks through Neuroevolution with Stochastic Gradient Descent

• URL: http://arxiv.org/abs/2012.11184v1
• Date: Mon, 21 Dec 2020 08:54:14 GMT
• Title: Optimizing Deep Neural Networks through Neuroevolution with Stochastic Gradient Descent
• Authors: Haichao Zhang, Kuangrong Hao, Lei Gao, Bing Wei, Xuesong Tang
• Abstract summary: gradient descent (SGD) is dominant in training a deep neural network (DNN) Neuroevolution is more in line with an evolutionary process and provides some key capabilities that are often unavailable in SGD. A hierarchical cluster-based suppression algorithm is also developed to overcome similar weight updates among individuals for improving population diversity.
• Score: 18.70093247050813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for training. Stochastic gradient descent (SGD) is dominant in training a DNN by adjusting neural network weights to minimize the DNNs loss function. As an alternative approach, neuroevolution is more in line with an evolutionary process and provides some key capabilities that are often unavailable in SGD, such as the heuristic black-box search strategy based on individual collaboration in neuroevolution. This paper proposes a novel approach that combines the merits of both neuroevolution and SGD, enabling evolutionary search, parallel exploration, and an effective probe for optimal DNNs. A hierarchical cluster-based suppression algorithm is also developed to overcome similar weight updates among individuals for improving population diversity. We implement the proposed approach in four representative DNNs based on four publicly-available datasets. Experiment results demonstrate that the four DNNs optimized by the proposed approach all outperform corresponding ones optimized by only SGD on all datasets. The performance of DNNs optimized by the proposed approach also outperforms state-of-the-art deep networks. This work also presents a meaningful attempt for pursuing artificial general intelligence.

Related papers

• Unveiling the Power of Sparse Neural Networks for Feature Selection [60.50319755984697]
  Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. We show that SNNs trained with dynamic sparse training (DST) algorithms can achieve, on average, more than $50%$ memory and $55%$ FLOPs reduction. Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than $50%$ memory and $55%$ FLOPs reduction.
  arXiv  Detail & Related papers  (2024-08-08T16:48:33Z)
• Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods [33.377770671553336]
  Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial neural networks (ANNs) In this paper, we provide a new perspective to summarize the theories and methods for training deep SNNs with high performance.
  arXiv  Detail & Related papers  (2024-05-06T09:58:54Z)
• Adversarially Robust Spiking Neural Networks Through Conversion [16.2319630026996]
  Spiking neural networks (SNNs) provide an energy-efficient alternative to a variety of artificial neural network (ANN) based AI applications. As the progress in neuromorphic computing with SNNs expands their use in applications, the problem of adversarial robustness of SNNs becomes more pronounced.
  arXiv  Detail & Related papers  (2023-11-15T08:33:46Z)
• A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks [53.31941519245432]
  Brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks. These SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation. In this study, we argue that SNN architectures should be holistically designed to incorporate heterogeneous coding schemes.
  arXiv  Detail & Related papers  (2023-05-26T02:52:12Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff [33.91830001268308]
  Spiking neural network (SNN) offers promising improvements in computational efficiency. Current SNN training methodologies predominantly employ a fixed timestep approach. We propose to consider cutoff in SNN, which can terminate SNN anytime during the inference to achieve efficient inference.
  arXiv  Detail & Related papers  (2023-01-23T16:14:09Z)
• Neuron Coverage-Guided Domain Generalization [37.77033512313927]
  This paper focuses on the domain generalization task where domain knowledge is unavailable, and even worse, only samples from a single domain can be utilized during training. Our motivation originates from the recent progresses in deep neural network (DNN) testing, which has shown that maximizing neuron coverage of DNN can help to explore possible defects of DNN.
  arXiv  Detail & Related papers  (2021-02-27T14:26:53Z)
• Exploiting Heterogeneity in Operational Neural Networks by Synaptic Plasticity [87.32169414230822]
  Recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs) In this study the focus is drawn on searching the best-possible operator set(s) for the hidden neurons of the network based on the Synaptic Plasticity paradigm that poses the essential learning theory in biological neurons. Experimental results over highly challenging problems demonstrate that the elite ONNs even with few neurons and layers can achieve a superior learning performance than GIS-based ONNs.
  arXiv  Detail & Related papers  (2020-08-21T19:03:23Z)
• Bayesian Graph Neural Networks with Adaptive Connection Sampling [62.51689735630133]
  We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) The proposed framework not only alleviates over-smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs.
  arXiv  Detail & Related papers  (2020-06-07T07:06:35Z)
• Genetic Algorithmic Parameter Optimisation of a Recurrent Spiking Neural Network Model [0.6767885381740951]
  We use genetic algorithm (GA) to search for optimal parameters in recurrent spiking neural networks (SNNs) We consider a cortical column based SNN comprising 1000 Izhikevich spiking neurons for computational efficiency and biologically realism. We show that the GA optimal population size was within 16-20 while the crossover rate that returned the best fitness value was 0.95.
  arXiv  Detail & Related papers  (2020-03-30T22:44:04Z)
• Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks [55.0627904986664]
  Spiking Neural Networks (SNNs) usetemporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation. This paper investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.
  arXiv  Detail & Related papers  (2020-03-26T11:13:07Z)

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.