# Practical Block-wise Neural Network Architecture Generation

Source: [Practical Block-wise Neural Network Architecture Generation](<https://www.sota2.com/research/paper/68fa64631e209131cea043fa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:02:11.964Z

Authors: Zhao Zhong, Junjie Yan, Wei Wu, Jing Shao, Cheng-Lin Liu

Published: 2017-08-18T10:12:43.000Z

## Abstract

Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained sequentially to choose component layers. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it performs competitive results in comparison to the hand-crafted state-of-the-art networks on image classification, additionally, the best network generated by BlockQNN achieves 3.54% top-1 error rate on CIFAR-10 which beats all existing auto-generate networks. (2) in the meanwhile, it offers tremendous reduction of the search space in designing networks which only spends 3 days with 32 GPUs, and (3) moreover, it has strong generalizability that the network built on CIFAR also performs well on a larger-scale ImageNet dataset.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-100 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test.md>): Image Classification; CIFAR-100 (test); Accuracy: not recorded.

- [Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1708.05552>)

[PDF](<https://arxiv.org/pdf/1708.05552.pdf>)
