Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks

Tools

Akten, Memo and Grierson, Mick. 2016. 'Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks'. In: Constructive Machine Learning Workshop, NIPS 2016. Barcelona, Spain 10 Dec 2016. [Conference or Workshop Item]

Preview

Text
mcts_cnn.pdf - Published Version
Available under License Creative Commons Attribution.
Download (1MB) | Preview

Official URL: http://www.cs.nott.ac.uk/~psztg/cml/2016/

Abstract or Description

We investigate a human-machine collaborative drawing environment in which an autonomous agent sketches images while optionally allowing a user to directly influence the agent's trajectory. We combine Monte Carlo Tree Search with image classifiers and test both shallow models (e.g. multinomial logistic regression) and deep Convolutional Neural Networks (e.g. LeNet, Inception v3). We found that using the shallow model, the agent produces a limited variety of images, which are noticably recogonisable by humans. However, using the deeper models, the agent produces a more diverse range of images, and while the agent remains very confident (99.99%) in having achieved its objective, to humans they mostly resemble unrecognisable 'random' noise. We relate this to recent research which also discovered that 'deep neural networks are easily fooled' \cite{Nguyen2015} and we discuss possible solutions and future directions for the research.

Item Type:

Conference or Workshop Item (Poster)

Keywords:

collaborative, agent, creativity, artificial intelligence, monte carlo tree search, deep learning, convolutional neural networks

Related URLs: