101 - The Lottery Ticket Hypothesis, With Jonathan Frankle NLP Highlights podcast

Artwork

Artificial Intelligence Tech Science NLP Highlights Allen Institute for Artificial Intelligence Tell Us

Indhold leveret af NLP Highlights and Allen Institute for Artificial Intelligence. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af NLP Highlights and Allen Institute for Artificial Intelligence eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.

NLP Highlights « »
101 - The lottery ticket hypothesis, with Jonathan Frankle

5y ago 41:16

Del

MP3•Episode hjem

Indhold leveret af NLP Highlights and Allen Institute for Artificial Intelligence. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af NLP Highlights and Allen Institute for Artificial Intelligence eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.

In this episode, Jonathan Frankle describes the lottery ticket hypothesis, a popular explanation of how over-parameterization helps in training neural networks. We discuss pruning methods used to uncover subnetworks (winning tickets) which were initialized in a particularly effective way. We also discuss patterns observed in pruned networks, stability of networks pruned at different time steps and transferring uncovered subnetworks across tasks, among other topics. A recent paper on the topic by Frankle and Carbin, ICLR 2019: https://arxiv.org/abs/1803.03635 Jonathan Frankle’s homepage: http://www.jfrankle.com/

… continue reading

145 episoder

#Artificial Intelligence #Tech #Science #NLP Highlights #Allen Institute for Artificial Intelligence #Tell Us

Artwork

101 - The lottery ticket hypothesis, with Jonathan Frankle

286 subscribers

published 5y ago

Del

MP3•Episode hjem

Indhold leveret af NLP Highlights and Allen Institute for Artificial Intelligence. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af NLP Highlights and Allen Institute for Artificial Intelligence eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.

In this episode, Jonathan Frankle describes the lottery ticket hypothesis, a popular explanation of how over-parameterization helps in training neural networks. We discuss pruning methods used to uncover subnetworks (winning tickets) which were initialized in a particularly effective way. We also discuss patterns observed in pruned networks, stability of networks pruned at different time steps and transferring uncovered subnetworks across tasks, among other topics. A recent paper on the topic by Frankle and Carbin, ICLR 2019: https://arxiv.org/abs/1803.03635 Jonathan Frankle’s homepage: http://www.jfrankle.com/

… continue reading

145 episoder

#Artificial Intelligence #Tech #Science #NLP Highlights #Allen Institute for Artificial Intelligence #Tell Us

Όλα τα επεισόδια

×

Velkommen til Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

Lyt til 500+ emner

Lyt til dette show, mens du udforsker