• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    One Layer Deeper drew over 15,000 submissions, but reportedly nobody solved it as intended

    Core Automation describes what worked across 15,602 submissions to the competition.

    RA
    MS
    CA
    7 Sources, ,

    TLDR

    Core Automation describes what worked across 15,602 submissions to the One Layer Deeper competition. A user sharing the write-up says nobody solved the problem as intended, but highlights interesting ideas for learning reusable operations and composing them into deeper computations.

    Combined views

    38.4K

    7 Sources, first seen 18d ago

    Combined views

    38.4K

    7 Sources, first seen 18d ago

    343 likes
    18d ago
    first seen 18d ago
    343 likes
    18 comments
    168 saves
    44 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    18 comments
    168 saves
    44 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    7 Sources

    @marksaroufimOver 15,000 submissions to One Layer Deeper. Nobody solved the problem as intended, but there are some interesting ideas for learning reusable operations and composing them into deeper computations https://www.coreauto.com/blog/what-the-models-learned-in-one-layer-deeper
    @coreautoDeep learning is still not solved. It has been great to see the creativity of the community and we all have more work to do to understand the universe. Thank you for being in this journey together ❤️
    @varunnealThough this challenge was impossible I learned a lot trying to attempt it anyway. For example, I learned that backprop is capable of factoring small semiprimes. This is contrary to the intent of the problem!
    @_arohan_RT @varunneal: Though this challenge was impossible I learned a lot trying to attempt it anyway. For example, I learned that backprop is ca…

    7 Sources

    @marksaroufimOver 15,000 submissions to One Layer Deeper. Nobody solved the problem as intended, but there are some interesting ideas for learning reusable operations and composing them into deeper computations https://www.coreauto.com/blog/what-the-models-learned-in-one-layer-deeper
    @coreautoDeep learning is still not solved. It has been great to see the creativity of the community and we all have more work to do to understand the universe. Thank you for being in this journey together ❤️
    @varunnealThough this challenge was impossible I learned a lot trying to attempt it anyway. For example, I learned that backprop is capable of factoring small semiprimes. This is contrary to the intent of the problem!
    @_arohan_RT @varunneal: Though this challenge was impossible I learned a lot trying to attempt it anyway. For example, I learned that backprop is ca…