Optimizing Deep Neural Networks through Neuroevolution with Stochastic Gradient Descent Article Swipe

MAKE IMPACT

Haichao Zhang , Kuangrong Hao , Lei Gao , Bing Wei , Xue‐song Tang · YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2012.11184

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.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2012.11184

PDF

https://arxiv.org/pdf/2012.11184

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4285708251

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4285708251

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2012.11184

Digital Object Identifier

Title

Optimizing Deep Neural Networks through Neuroevolution with Stochastic Gradient Descent

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2020

Year of publication

Publication date

2020-12-21

Full publication date if available

Authors

Haichao Zhang, Kuangrong Hao, Lei Gao, Bing Wei, Xue‐song Tang

List of authors in order

Landing page

https://arxiv.org/abs/2012.11184

Publisher landing page

PDF URL

https://arxiv.org/pdf/2012.11184

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2012.11184

Direct OA link when available

Concepts

Neuroevolution, Computer science, Stochastic gradient descent, Artificial intelligence, Artificial neural network, Deep neural networks, Gradient descent, Machine learning, Evolutionary algorithm, Heuristic

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2023: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload