ptPortuguês

Yannic Kilcher

Name: Neural Architecture Search without Training (Paper Explained)
Uploaded: 2020-07-21T13:00:01.000Z

I make videos about machine learning research papers, programming, and issues of the AI community, and the broader impact of AI in society.

Canal oficial no YouTube ↗

Vídeos: 487
Inscritos: 333 mil
Visualizações totais: 18,3 mi
Últimos envios: 6 de mar. de 2026

Página independente
Machine Learning
Idioma do conteúdo: inglês
Região: Suíça

Esta é uma página de diretório independente operada pelo Youtop. Não é operada, patrocinada nem endossada por Yannic Kilcher ou pelo YouTube. Canal oficial no YouTube ↗Sugerir uma correção Você é este criador? Reivindique esta página

Neural Architecture Search without Training (Paper Explained) — Yannic Kilcher · Youtop

Neural Architecture Search without Training (Paper Explained)

Yannic Kilcher · Publicado em 21 de julho de 2020

Assistir no YouTube ↗

Dos metadados do YouTube

#ai #research #machinelearning Neural Architecture Search is typically very slow and resource-intensive. A meta-controller has to train many hundreds or thousands of different models to find a suitable building plan. This paper proposes to use statistics of the Jacobian around data points to estimate the performance of proposed architectures at initialization. This method does not require training and speeds up NAS by orders of magnitude. OUTLINE: 0:00 - Intro & Overview 0:50 - Neural Architecture Search 4:15 - Controller-based NAS 7:35 - Architecture Search Without Training 9:30 - Linearization Around Datapoints 14:10 - Linearization Statistics 19:00 - NAS-201 Benchmark 20:15 - Experiments 34:15 - Conclusion & Comments Paper: https://arxiv.org/abs/2006.04647 Code: https://github.com/BayesWatch/nas-without-training Abstract: The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be extremely slow and expensive; they need to train vast numbers of candidate networks to inform the search process. This could be remedied if we could infer a network's trained accuracy from its initial state. In this work, we examine how the linear maps induced by data points correlate for untrained network architectures in the NAS-Bench-201 search space, and motivate how this can be used to give a measure of modelling flexibility which is highly indicative of a network's trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU. Code to reproduce our experiments is available at this https URL. Authors: Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yannic-kilcher Minds: https://www.minds.com/ykilcher Parler: https://parler.com/profile/YannicKilcher LinkedIn: https://www.linkedin.com/in/yannic-kilcher-488534136/ If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar (preferred to Patreon): https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Mais de Yannic Kilcher

Ver tudo

13:46I BUILT A FULLY AUTOMATIC MANSPLAINER6 de mar. de 2026

Ao vivo2:33:37Traditional X-Mas Stream29 de dez. de 2025

Ao vivo0:00Traditional Holiday Live Stream28 de dez. de 2025

← Voltar para Yannic Kilcher