SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.07320 · 2019

EENA: Efficient Evolution of Neural Architecture

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

Latest algorithms for automatic neural architecture search perform remarkable but are basically directionless in search space and computational expensive in training of every intermediate architecture. In this paper, we propose a method for efficient architecture search called EENA (Efficient Evolution of Neural Architecture). Due to the elaborately designed mutation and crossover operations, the evolution process can be guided by the information have already been learned. Therefore, less computational effort will be required while the searching and training time can be reduced significantly. On CIFAR-10 classification, EENA using minimal computational resources (0.65 GPU-days) can design highly effective neural architecture which achieves 2.56% test error with 8.47M parameters. Furthermore, the best architecture discovered is also transferable for CIFAR-100.

For agents

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

get_harvested_code_for_paper("1905.07320")
get_code_for_paper("1905.07320")
have("1905.07320")

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

curl https://syntology.ai/api/ran/1905.07320.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.07320.svg)](https://syntology.ai/paper/1905.07320)

Connect an agent — have() is free.