pith. sign in

arxiv: 1802.01548 · v7 · pith:V2NU6Y77new · submitted 2018-02-05 · 💻 cs.NE · cs.AI· cs.CV· cs.DC

Regularized Evolution for Image Classifier Architecture Search

classification 💻 cs.NE cs.AIcs.CVcs.DC
keywords imageevolutionsearchaccuracyalgorithmamoebanet-aarchitectureclassifiers
0
0 comments X
read the original abstract

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have been repeatedly applied to neural network topologies, the image classifiers thus discovered have remained inferior to human-crafted ones. Here, we evolve an image classifier---AmoebaNet-A---that surpasses hand-designs for the first time. To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. Matching size, AmoebaNet-A has comparable accuracy to current state-of-the-art ImageNet models discovered with more complex architecture-search methods. Scaled to larger size, AmoebaNet-A sets a new state-of-the-art 83.9% / 96.6% top-5 ImageNet accuracy. In a controlled comparison against a well known reinforcement learning algorithm, we give evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search. This is relevant when fewer compute resources are available. Evolution is, thus, a simple method to effectively discover high-quality architectures.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

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

  1. Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data

    cs.LG 2023-10 unverdicted novelty 7.0

    Experimental comparison of 15 HPO and NAS algorithms for automated feature preprocessing on 45 tabular datasets finds evolution-based methods and random search as top performers.

  2. Video Action Recognition Via Neural Architecture Searching

    cs.CV 2019-07 unverdicted novelty 6.0

    Uses differentiable NAS with temporal segments and pseudo-3D operators to discover a video action recognition network that outperforms hand-designed models on UCF101 with ~1% of the parameters when trained from scratch.

  3. Neural Input Search for Large Scale Recommendation Models

    cs.LG 2019-07 unverdicted novelty 6.0

    NIS applies RL to jointly optimize per-feature vocabulary sizes and per-value embedding dimensions under memory constraint, reporting 6.8% Recall@1 and 1.8% ROC-AUC gains over manual baselines on retrieval and ranking tasks.

  4. Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging

    cs.NE 2026-05 unverdicted novelty 5.0

    Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller sea...

  5. EPNAS: Efficient Progressive Neural Architecture Search

    cs.LG 2019-07 unverdicted novelty 5.0

    EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNe...

  6. Genetic Network Architecture Search

    cs.NE 2019-07 unverdicted novelty 3.0

    Genetic algorithm searches convolution cell architectures with weight sharing via SGD, reporting 96% accuracy on CIFAR10 and 80.1% on CIFAR100.