A genetic programming approach to designing convolutional neural network architectures

By Masanori Suganuma, Shinichi Shirakawa, Tomoharu Nagao. 2017

618 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Model Architectures, Neural Architecture Search & AutoML

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Quoc V. Le
  2. Frank Hutter
  3. Mengjie Zhang
  4. Bing Xue
  5. Martin Wistuba
  6. Yanan Sun
  7. Gary G. Yen
  8. Xia Hu

In Model Architectures

  1. Frank Hutter
  2. Martin Wistuba
  3. Junjie Yan
  4. Mengjie Zhang
  5. Thomas Elsken
  6. Yanan Sun
  7. Bing Xue
  8. Gary G. Yen

In Neural Architecture Search & AutoML

  1. Frank Hutter
  2. Quoc V. Le
  3. Martin Wistuba
  4. Thomas Elsken
  5. Xia Hu
  6. Qingquan Song
  7. Jan Hendrik Metzen
  8. Yanan Sun

Citations in the corpus