Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks
This work addresses the challenge of aligning AI creativity with human perception in collaborative drawing, though it is incremental as it builds on known issues like deep neural networks being easily fooled.
The study explored a human-machine collaborative drawing system using Monte Carlo Tree Search with image classifiers, finding that shallow models produced limited but recognizable images, while deep Convolutional Neural Networks generated diverse images that were mostly unrecognizable noise to humans, despite high agent confidence.
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.