DeepAI AI Chat
Log In Sign Up

Digits that are not: Generating new types through deep neural nets

by   Akın Kazakçıand Mehdi Cherti, et al.
MINES ParisTech

For an artificial creative agent, an essential driver of the search for novelty is a value function which is often provided by the system designer or users. We argue that an important barrier for progress in creativity research is the inability of these systems to develop their own notion of value for novelty. We propose a notion of knowledge-driven creativity that circumvent the need for an externally imposed value function, allowing the system to explore based on what it has learned from a set of referential objects. The concept is illustrated by a specific knowledge model provided by a deep generative autoencoder. Using the described system, we train a knowledge model on a set of digit images and we use the same model to build coherent sets of new digits that do not belong to known digit types.


page 2

page 5

page 6

page 7


NQMIX: Non-monotonic Value Function Factorization for Deep Multi-Agent Reinforcement Learning

Multi-agent value-based approaches recently make great progress, especia...

A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs

Exploration in environments which differ across episodes has received in...

Uncertainty-sensitive Learning and Planning with Ensembles

We propose a reinforcement learning framework for discrete environments ...

Universal Successor Representations for Transfer Reinforcement Learning

The objective of transfer reinforcement learning is to generalize from a...

Gamma-Nets: Generalizing Value Estimation over Timescale

We present Γ-nets, a method for generalizing value function estimation o...

Shapley Sets: Feature Attribution via Recursive Function Decomposition

Despite their ubiquitous use, Shapley value feature attributions can be ...

Enhanced Scene Specificity with Sparse Dynamic Value Estimation

Multi-scene reinforcement learning involves training the RL agent across...