mlsanityData to 7 Oct 2026

A Genetic Programming Approach to Designing Convolutional Neural Network Architectures

arXiv 1704.00764 ↗First posted 3 Apr 2017cs.NEcited by 59

Not on the map. Why?

Abstract (arXiv)

The convolutional neural network (CNN), which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, we attempt to automatically construct CNN architectures for an image classification task based on Cartesian genetic programming (CGP). In our method, we adopt highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The CNN structure and connectivity represented by the CGP encoding method are optimized to maximize the validation accuracy. To evaluate the proposed method, we constructed a CNN architecture for the image classification task with the CIFAR-10 dataset. The experimental result shows that the proposed method can be used to automatically find the competitive CNN architecture compared with state-of-the-art models.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 18; 2023: 10; 2024: 5; 2025: 3; 2026: 5.

59 papers.

Sort:

  1. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  2. 2022Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessmentcited by 17
  3. 2024Knowledge Fusion By Evolving Weights of Language Modelscited by 16
  4. 2021One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinkingcited by 12
  5. 2022A Survey on Computationally Efficient Neural Architecture Searchcited by 12
  6. 2021iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretizationcited by 10
  7. 2021NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameterscited by 9
  8. 2022Less is More: Proxy Datasets in NAS approachescited by 9
  9. 2022A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trendscited by 9
  10. 2023Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologiescited by 9
  11. 2022PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Searchcited by 8
  12. 2021A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networkscited by 7
38 more
  1. 2021Search For Deep Graph Neural Networkscited by 6
  2. 2024Robust NAS under adversarial training: benchmark, theory, and beyondcited by 6
  3. 2021Enhanced Gradient for Differentiable Architecture Searchcited by 5
  4. 2021Graph-based Neural Architecture Search with Operation Embeddingscited by 5
  5. 2021Manas: Mining Software Repositories to Assist AutoMLcited by 5
  6. 2022Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligencecited by 5
  7. 2022Exploring the Intersection between Neural Architecture Search and Continual Learningcited by 4
  8. 2022ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approachcited by 4
  9. 2022AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Imagescited by 4
  10. 2023DQNAS: Neural Architecture Search using Reinforcement Learningcited by 4
  11. 2023AutoML for Large Capacity Modeling of Meta's Ranking Systemscited by 4
  12. 2023Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systemscited by 3
  13. 2021A Novel Framework for Neural Architecture Search in the Hill Climbing Domaincited by 2
  14. 2021HALF: Holistic Auto Machine Learning for FPGAscited by 2
  15. 2021Experiments on Properties of Hidden Structures of Sparse Neural Networkscited by 2
  16. 2022PSO-Convolutional Neural Networks with Heterogeneous Learning Ratecited by 2
  17. 2022An Adaptive and Stability-Promoting Layerwise Training Approach for Sparse Deep Neural Network Architecturecited by 2
  18. 2023A Survey on Multi-Objective based Parameter Optimization for Deep Learningcited by 2
  19. 2025Topological derivative approach for deep neural network architecture adaptationcited by 2
  20. 2026Bilevel Optimization for Neural Architecture Searchcited by 2
  21. 2021Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architecturescited by 1
  22. 2021Evolving Architectures with Gradient Misalignment toward Low Adversarial Transferabilitycited by 1
  23. 2021Evolving Transferable Neural Pruning Functionscited by 1
  24. 2022Efficient Search of Multiple Neural Architectures with Different Complexities via Importance Samplingcited by 1
  25. 2023Continuous Cartesian Genetic Programming based representation for Multi-Objective Neural Architecture Searchcited by 1
  26. 2023DREAM: Debugging and Repairing AutoML Pipelinescited by 1
  27. 2024Random forests for detecting weak signals and extracting physical information: a case study of magnetic navigationcited by 1
  28. 2024ApproxDARTS: Differentiable Neural Architecture Search with Approximate Multiplierscited by 1
  29. 2021Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Networkcited by 0
  30. 2021Trainless Model Performance Estimation for Neural Architecture Searchcited by 0
  31. 2021Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNNcited by 0
  32. 2021ConAM: Confidence Attention Module for Convolutional Neural Networkscited by 0
  33. 2022HDAM: Heuristic Difference Attention Module for Convolutional Neural Networkscited by 0
  34. 2022ERNAS: An Evolutionary Neural Architecture Search for Magnetic Resonance Image Reconstructionscited by 0
  35. 2022Adversarial Robustness Assessment of NeuroEvolution Approachescited by 0
  36. 2022MEESO: A Multi-objective End-to-End Self-Optimized Approach for Automatically Building Deep Learning Modelscited by 0
  37. 2022An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networkscited by 0
  38. 2022Single Cell Training on Architecture Search for Image Denoisingcited by 0

50 most cited of 59 All 59 (JSON)