Pith. sign in

REVIEW 2 cited by

Evolutionary-Neural Hybrid Agents for Architecture Search

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1811.09828 v4 pith:BR2PIZOY submitted 2018-11-24 cs.LG cs.NEstat.ML

classification cs.LGcs.NEstat.ML
keywords searchagentsarchitectureevo-nasneuralagentclassificationevolutionary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is critical for such a resource intensive application. In order to capture the best of both worlds, we propose a class of Evolutionary-Neural hybrid agents (Evo-NAS). We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks. On a high-complexity architecture search space for image classification, the Evo-NAS agent surpasses the accuracy achieved by commonly used agents with only 1/3 of the search cost.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Scalable Reinforcement-Learning-Based Neural Architecture Search for Cancer Deep Learning Research

    cs.LG 2019-09 conditional novelty 5.0 of 10

    Reinforcement-learning-based neural architecture search finds smaller and faster neural networks with accuracy comparable to, or better than, manually designed networks on three cancer drug-response benchmarks.

  2. AutoML: A Survey of the State-of-the-Art

    cs.LG 2019-08 unverdicted novelty 1.0 of 10

    A survey that organizes AutoML into a four-stage pipeline and reviews neural architecture search methods, their performance, and open problems.

Pith tools