korrents

A korrentour readingWhat is a korrent?

The saving pruning offers is only ever at inference, because the sparse architectures it produces are hard to train from the start.

Drawn from what Michael Carbin and Jonathan Frankle said

Subjectpruning
What this subject means

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

Interesting
A private bookmark. Not a position, and never counted.

What they actually said

Word for word, with the source under each one. They did not write this page.

  1. Michael Carbin However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance. arxiv.org

    Associate professor at MIT

    Their wordsHowever, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance.

    Where this was said

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

    All 10 korrents from this piecethis one is 4th

  2. Jonathan Frankle However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance. arxiv.org

    Chief AI scientist at Databricks

    Their wordsHowever, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance.

    Where this was said

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

    All 10 korrents from this piecethis one is 3rd

Added to korrents 9 Mar 2018 · How quotes work · Something wrong? Tell us

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

Sign in to record that you hold this, with a confidence number of your own.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

On the map

Loading the map… or open it on its own page

Open the map on its own page →