hackertube.io

Brains, Sex, and Machine Learning

Google TechTalks · talk · Watch on YouTube

Machine learning & deep learningNeuroscience & the brain

What it is

Geoffrey Hinton's Google Tech Talk linking machine learning to biology, explaining dropout as a form of model averaging and why sexual reproduction and stochastic spiking neurons may prevent overfitting.

Why Hacker News recommends it

Recommended as a simple, elegant explanation of dropout and its connection to how the brain works.

  • 7 people recommended it
  • 5 different months
  • 3 strong recommendations
  • first 2012, last 2017

What HN commenters said

  1. “Here is a GREAT talk by Geoffrey Hinton”

    Hinton explains dropout and its link to how brains work.

    FrojoS, 2012-11 · Strong recommendation · in “Microsoft turns spoken English into spoken Mandarin – in the same voice”

  2. “the extraordinary simple and elegant talk by G. Hinton last summer”

    Simple, elegant talk linking dropout to why neurons use spikes.

    pilooch, 2013-05 · Strong recommendation · in “Andrew Ng and the Quest for the New AI”

  3. “I would highly recommend this video”

    Hinton's 2012 talk related to low-multiplication neural network research.

    eveningcoffee, 2015-11 · Strong recommendation · in “Neural Networks with Few Multiplications”

  4. “watch Hinton describe it in a recent talk he gave at Google”

    Hinton describes dropout training as model averaging.

    psb217, 2012-12 · Recommendation · in “Why use SVM”

  5. “If you want a great overview of the dropout technique, watch this tech talk by Hinton”

    Great overview of the dropout technique.

    lightcatcher, 2013-05 · Recommendation · in “Unsupervised Feature Learning and Deep Learning Tutorial”

  6. “has a very stimulating pair of hypotheses related to this”

    Hinton on dropout, bagging, and why sex and spiking neurons might prevent overfitting.

    taliesinb, 2013-05 · Recommendation · in “Machine Learning as a Service”

  7. “sheds interesting light on some variants of deep learning and the way the brain uses (classical) noise”

    Sheds light on deep learning variants and the brain's use of noise.

    carlob, 2014-02 · Recommendation · in “AI”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: geoffrey hinton, dropout, deep learning, spiking neurons, overfitting

Also recommended by the same people