Skip to main content Skip to navigation

Warwick Annual Retreat Projects

Warwick Annual Retreat Projects Fun with Generative Models

You need to be logged in to post in this topic.
  1. Fun with Generative Models

    Organised by Iliana Peneva

    Abstract

    Neural networks have been used for almost everything: to train a robot how to play football; to generate April Fools jokes/names of metal bands/traditional Irish music/candy heart messages, to distinguish between chihuahua and muffin, to generate cats from drawings. Inspired by Rob's entertaining WARP from 2 years ago and by Janelle Shane's brilliant blog, my proposed project aims to add to this list of fun NNs applications by generating new dog/cat breeds, DnD spells, Pokemons, cake recipes, talk abstracts, news items.

    We can decide what to generate at the retreat (there can be people working on different topics)
    Suggestions are welcome for other topics :-)

    Aims and Objectives

    • learn more about different types of neural networks, their capabilities and limitations
    • get experience using neural networks in Python/R

    Of Interest to

    Anyone interested in deep learning (or likes cats/dogs/cakes/DnD/Pokemon)

    Resources Necessary 
    The datasets will be collected and made available before the retreat.

    if using Python - Keras and Tensorflow; if using R - neuralnet, or Keras and Tensorflow for R

    References 
    (most relevant)
    Andrey Karpathy's excellent blogpost with examples: http://karpathy.github.io/2015/05/21/rnn-effectiveness/
    Christopher Olah's blogpost: http://colah.github.io/posts/2015-08-Understanding-LSTMs/

    (for the keener)
    Deep Leaning book by Ian Godfellow, Yoshua Bengio, Aaron Courville: http://www.deeplearningbook.org/contents/rnn.html

     
  2. Here are the first few datasets: https://drive.google.com/drive/folders/1OSWWJDyPm305_GuUmg_64rvyaoHxyHCq?usp=sharing 

    These include: cats, dogs, Pokemon, DnD spells (5th edition), wrestlers' names (thanks to Jack :-) ) and rom coms. I will upload the talk abstracts from previous annual retreats and cake recipes later this week.  

     

Are you sure?

Are you sure?

Forum followers

Follower data is not currently available.

Search results

Checklist

  • The problem should not be part of your PhD!
  • Expected group sizes of 4-5 people
  • Officially allocated time is of about 6 hours (although hopefully you'll continue working outside of these!)


Ideas to get you started