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

Abstract

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.

Presented at the Constructive Machine Learning workshop at NIPS 2016 as a poster and spotlight talk. 8 pages including 2 page references, 2 page appendix, 3 figures. Blog post (including videos) at https://medium.com/@memoakten/collaborative-creativity-with-monte-carlo-tree-search-and-convolutional-neural-networks-and-other-69d7107385a0

References in corpus (6)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Playing Atari with Deep Reinforcement Learning
• Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
• Visualizing and Understanding Convolutional Networks
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Understanding Deep Image Representations by Inverting Them