Structure Learning of Deep Neural Networks with Q-Learning
This addresses the high cost of manual network design for researchers and practitioners, though it is incremental by building on existing block designs and reinforcement learning methods.
The paper tackles the problem of automatically designing neural network architectures by using Q-learning to sequentially select and combine multiple block types (e.g., Inception, residual, dense blocks), achieving comparable or better performance than hand-crafted and other auto-generated networks on MNIST, SVHN, and CIFAR-10 datasets.
Recently, with convolutional neural networks gaining significant achievements in many challenging machine learning fields, hand-crafted neural networks no longer satisfy our requirements as designing a network will cost a lot, and automatically generating architectures has attracted increasingly more attention and focus. Some research on auto-generated networks has achieved promising results. However, they mainly aim at picking a series of single layers such as convolution or pooling layers one by one. There are many elegant and creative designs in the carefully hand-crafted neural networks, such as Inception-block in GoogLeNet, residual block in residual network and dense block in dense convolutional network. Based on reinforcement learning and taking advantages of the superiority of these networks, we propose a novel automatic process to design a multi-block neural network, whose architecture contains multiple types of blocks mentioned above, with the purpose to do structure learning of deep neural networks and explore the possibility whether different blocks can be composed together to form a well-behaved neural network. The optimal network is created by the Q-learning agent who is trained to sequentially pick different types of blocks. To verify the validity of our proposed method, we use the auto-generated multi-block neural network to conduct experiments on image benchmark datasets MNIST, SVHN and CIFAR-10 image classification task with restricted computational resources. The results demonstrate that our method is very effective, achieving comparable or better performance than hand-crafted networks and advanced auto-generated neural networks.