korrents

Our readingWhat is a korrent?

A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.

Drawn from what Michael Carbin and Jonathan Frankle said

Subjectsneural networkspruning
What these subjects mean

neural networks The architecture almost all modern machine learning is built on, and what changes when it gets deeper.

pruning Cutting connections that are not doing the work — in a trained network, and in a developing brain.

What they actually said

  1. Michael Carbin Associate professor at MIT Above this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy. Frankle & Carbin, "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" (arXiv)arxiv.org · 9 Mar 2018All 10 korrents from this piece
    Their wordsAbove this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy.

    Where this was said

    ↗Frankle & Carbin, "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" (arXiv)arxiv.org

    9 Mar 2018

    All 10 korrents from this piecethis one is 10th

  2. Jonathan Frankle Chief AI scientist at Databricks Above this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy. Frankle & Carbin, "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" (arXiv)arxiv.org · 9 Mar 2018All 10 korrents from this piece
    Their wordsAbove this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy.

    Where this was said

    ↗Frankle & Carbin, "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" (arXiv)arxiv.org

    9 Mar 2018

    All 10 korrents from this piecethis one is 9th

Added to korrents 9 Sept 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map