SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.05285 · 2018

IRLAS: Inverse Reinforcement Learning for Architecture Search

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we propose an inverse reinforcement learning method for architecture search (IRLAS), which trains an agent to learn to search network structures that are topologically inspired by human-designed network. Most existing architecture search approaches totally neglect the topological characteristics of architectures, which results in complicated architecture with a high inference latency. Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt). To avoid raising a too strong prior over the search space, we introduce inverse reinforcement learning to train the mirror stimuli function and exploit it as a heuristic guidance for architecture search, easily generalized to different architecture search algorithms. On CIFAR-10, the best architecture searched by our proposed IRLAS achieves 2.60% error rate. For ImageNet mobile setting, our model achieves a state-of-the-art top-1 accuracy 75.28%, while being 2~4x faster than most auto-generated architectures. A fast version of this model achieves 10% faster than MobileNetV2, while maintaining a higher accuracy.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1812.05285")
get_code_for_paper("1812.05285")
have("1812.05285")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1812.05285.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1812.05285.svg)](https://syntology.ai/paper/1812.05285)

Connect an agent — have() is free.