Genetic CNN

by   Lingxi Xie, et al.

The deep Convolutional Neural Network (CNN) is the state-of-the-art solution for large-scale visual recognition. Following basic principles such as increasing the depth and constructing highway connections, researchers have manually designed a lot of fixed network structures and verified their effectiveness. In this paper, we discuss the possibility of learning deep network structures automatically. Note that the number of possible network structures increases exponentially with the number of layers in the network, which inspires us to adopt the genetic algorithm to efficiently traverse this large search space. We first propose an encoding method to represent each network structure in a fixed-length binary string, and initialize the genetic algorithm by generating a set of randomized individuals. In each generation, we define standard genetic operations, e.g., selection, mutation and crossover, to eliminate weak individuals and then generate more competitive ones. The competitiveness of each individual is defined as its recognition accuracy, which is obtained via training the network from scratch and evaluating it on a validation set. We run the genetic process on two small datasets, i.e., MNIST and CIFAR10, demonstrating its ability to evolve and find high-quality structures which are little studied before. These structures are also transferrable to the large-scale ILSVRC2012 dataset.


page 1

page 2

page 3

page 4


Hybrid Genetic Algorithm and Hill Climbing Optimization for the Neural Network

In this paper, we propose a hybrid model combining genetic algorithm and...

Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network

Hyperparameter optimization is a challenging problem in developing deep ...

An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints

Recently, there emerged revived interests of designing automatic program...

Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm

Convolutional Neural Networks (CNN) have gained great success in many ar...

A Cooperative Coevolutionary Genetic Algorithm for Learning Bayesian Network Structures

We propose a cooperative coevolutionary genetic algorithm for learning B...

Efficient Noisy Optimisation with the Sliding Window Compact Genetic Algorithm

The compact genetic algorithm is an Estimation of Distribution Algorithm...

ImmuNetNAS: An Immune-network approach for searching Convolutional Neural Network Architectures

In this research, we propose ImmuNetNAS, a novel Neural Architecture Sea...

Please sign up or login with your details

Forgot password? Click here to reset