2016/12/14 by Memo Akten, Akten, Memo, Mick Grierson +1
Computer Science · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #Data Visualization and Analytics #FOS: Computer and information sciences #Reinforcement Learning in Robotics #cs.AI
paper · pdf · doi:10.48550/arxiv.1612.04876
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
arxiv created 2016/12/14 · openalex publication_date 2016/12/14 · arxiv updated 2016/12/16 · openalex created_date 2017/01/06 · openalex updated_date 2026/07/28
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' \citeNguyen2015 and we discuss possible solutions and future directions for the research.