27 comments

  • vova_hn2 10 minutes ago

    > Your class is measured, not chosen

    > model and manifest bytes together pick the class

    What?

    How hard is it to write something like "your weight class is determined by the total size of the model and manifest" (if I understood it correctly).

    Current version both sounds very AI-sloppy and is ambiguous.

    The doc page [0] is even more painful to read.

    [0] https://tinybrains.dev/docs/models/weight-classes.html

  • Muthaalagan 24 minutes ago

    Interesting—how small can a neural network get and still make good strategic decisions? Curious whether these models can adapt to unfamiliar opponents.

  • awfm9 an hour ago

    Man, I remember doing this is 2011 as well. Everything some kind of hand-coded strategy. I enjoyed it a lot.

  • codetiger 21 hours ago

    15yrs back I participated in "Google Ants AI Challenge 2011", an ai programming competition, hosted by the University of Waterloo, and I ranked #127 (#1 in my country). The competition gave me a huge learning oppurtunity where developers across the world came to a forum and discussed various techniques.

    Now, I've built a similar platform to bring back the fun of building a small neural network that can play the game well. Neural Network optimization seems to be much more fun.

    Plz share your feedback to improve the platform and add more games.

    • Muthaalagan 20 minutes ago

      From competing with the world to building a place for the world to compete—what a full-circle moment. Love the challenge: how much strategy can a tiny neural network learn? Excited to see what people build.

    • AnotherGoodName 11 hours ago

      Nice. I was 72nd. Working in AI research today and still making ai for games as a hobby (tfmbot.com is an ai i’m working on for my favourite board game terraforming mars).

      • codetiger 10 hours ago

        Thanks for sharing. I remember #1 xathis had a score, big leap ahead of others. The difference in techniques in top 100 was almost the same.

    • atmanactive 17 hours ago

      I remember a game on Steam called Tiny Brains, great couch co-op.

  • adityamishra241 6 hours ago

    This looks fun. How do you evaluate the networks — is it purely based on game performance, or are there other metrics like size and inference speed too?

    • codetiger 3 hours ago

      Glad you like it. The evaluation is based purely on game performance. However each weight class is evaluated separately. Nano, micro, mini, small, large and open class.

      • codetiger 3 hours ago

        When you submit a model it participates on both its weight class and the open class

  • DylanMerigaud 5 hours ago

    Great idea to focus on small, efficient neural networks.

  • willmarch 9 hours ago

    Pretty neat! I'm considering entering some models. How long will you be running these competitions?

    • codetiger 9 hours ago

      The current season is a public beta and ends by end of the month. After that am considering 3 month seasons.

      • willmarch 3 hours ago

        Signed up and submitted a test model. Now the real training begins!

  • Qworg 8 hours ago

    Reminds me of MechMania at UIUC - exciting!

  • adityamishra241 19 hours ago

    This looks fun. How small are the networks you're aiming for?

    • sitzkrieg 13 hours ago

      the network size brackets are in TFA:

          nano up to 16 KiB
          micro up to 128 KiB 
          mini up to 1 MiB 
          small up to 8 MiB 
          large up to 64 MiB
    • codetiger 9 hours ago

      Each season has a different weight size restrictions. Currently open season is for a full production test.

  • cookiengineer 6 hours ago

    OMG!

    Just yesterday I published my reworked GoNEAT library that implements HyperNEAT combined with phased search and backpropagation [1].

    But it's kind of impossible to enter for me because of the hard pytorch requirements :( would love to see the project as a gym, so that you can run your own ANN design algorithm.

    I get that most data science students still use python, but the evolutionary world is kinda in C++ and other native languages.

    Anyways, great project nonetheless.

    [1] https://github.com/cookiengineer/goneat

    • codetiger 3 hours ago

      Where do you see a hard requirement? I have added support for ONNX model upload for now and would love to extend support for other formats. How you build the model is totally upto you. I don’t check anything other than format and inference time and model size.

    • codetiger 3 hours ago

      Saw your repo and understood you question better. The requirement are now limiting Neural Networks only, not a direct algorithm implementation

  • lostdog 11 hours ago

    Cool idea!

    It would help to delete all the text on the page, and write it without AI.

    For example, "model and manifest bytes together pick the class; every version also plays on Open"

    • codetiger 10 hours ago

      Thanks for the feedback. I’ll take that as top priority.

  • lokar 11 hours ago