korrents

A korrentour readingWhat is a korrent?

Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free.

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.

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 Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. arxiv.org

    Associate professor at MIT

    Their wordsNeural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy.

    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 2nd

  2. Jonathan Frankle Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. arxiv.org

    Chief AI scientist at Databricks

    Their wordsNeural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy.

    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 1st

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 →