IJCNN 2024 Special Session on Evolutionary Neural Computation

IJCNN 2024 Special Session on Evolutionary Neural Computation

Scope and Aim:

Evolutionary Computation (EC) and Neural Computation (NC) epitomize two distinctive yet complementary nature-inspired computational paradigms. From a bionic perspective, EC emulates evolutionary processes at the macro level, while NC simulates the intricate workings of neural systems at the micro level. Technically, EC encompasses a suite of algorithms dedicated to complex optimization tasks, whereas NC embodies a set of representation learning techniques aimed at intricate modeling challenges. The integration of these two paradigms is not only biologically coherent but also technically advantageous.

Fusion between EC and NC can fundamentally occur in two ways. Firstly, NC methodologies can be embedded within EC frameworks to enhance the search efficiency and effectiveness of EC algorithms. Secondly, EC strategies can be employed to augment the performance of NC models. Over the past decades, there has been significant advancement in both EC and NC in terms of algorithm development and application deployment. Despite these progresses, research dedicated to harnessing the synergies between EC and NC, particularly leveraging EC to bolster the capabilities of NC, remains nascent.

This special session seeks to convene researchers who are pioneering methods and applications at the crossroads of EC and NC. The goal is to foster a dynamic exchange of ideas, reveal new insights, and explore the untapped potential within this interdisciplinary domain.


Topics of interest include but are not limited to: 

  • Neural predictors for neural architecture search
  • Supernet training for neural architecture search
  • Encoding methods for neural architecture search
  • Visualization methods for neural architecture search
  • Evolutionary optimization for neural architecture search
  • Evolutionary optimization/training of neural networks
  • Evolutionary robotics
  • Evolutionary reinforcement learning
  • Artificial life via neuroevolution
  • Novelty search via neuroevolution
  • Evolutionary strategies for neuroevolution
  • Genetic programming for neuroevolution
  • GPU acceleration for neuroevolution
  • Estimation of distribution algorithms driven by neural networks
  • Surrogate-assisted evolutionary algorithms driven by neural networks
  • Evolutionary neural computation for applications, e.g., image classification, image semantic segmentation, natural language processing, engineering designs, etc.


Dr Zhichao Lu (luzhichaocn@gmail.com)

Department of Computer Science, City University of Hong Kong, HK

Dr Ran Cheng (ranchengcn@gmail.com)

Department of Computer Science and Engineering, Southern University of Science and Technology, China

Program Committee:

Brijesh Verma, Central Queensland University, Australia

Bing Xue, Victoria University of Wellington, New Zealand

Colin Johnson, University of Kent, UK

Felix Juefei-Xu, Meta AI & New York University, USA

Gary G. Yen, Oklahoma State University, USA

Grant Dick, University of Otago, New Zealand

Luziwei Leng, Huawei Technology, China

Mengjie Zhang, Victoria University of Wellington, New Zealand

Min Jiang, Xiamen University, China

Nasser R. Sabar, La Trobe University, Australia

Vishnu N. Boddeti, Michigan State University, USA

Yanan Sun, Sichuan University, China

Yu Xue, Nanjing University of Information Science and Technology, China


您的电子邮箱地址不会被公开。 必填项已用*标注