AI-ON Consciousness Prior
Switch branches/tags
Nothing to show
Clone or download
liamb315 Merge pull request #15 from duguyue100/master
update a moving mnist implementation
Latest commit 5f30aae Feb 1, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
src update some billiards features Jan 30, 2018
.gitignore update a moving mnist implementation Jan 25, 2018 Fix second Slack link Dec 21, 2017

The Consciousness Prior

Project Status:

  • Initial exploration of consciousness prior in a purely observational setting.
  • Constructing environments to test efficacy of CP in tracking objects, particularly when the task is complicated with high-entropy observations in the pixel space.

Community Links:

Problem description:

See introduction of project proposal.

Why this problem matters:

See introduction of project proposal.

How to measure success:

See introduction of project proposal.


  • Observational datasets will initially be synthetic. We propose a generalization to the Billiards task introduced in Sutskever et al.(2009)

Extracting Data - Preprocessing details:

  • Data will initially be synthetic.

Relevant Work:

Below you will find other relevant material to this project. This short list already assumes a familiarity with common deep neural networks (RNNs, CNNs) and training procedures (BPTT).


To contribute to this project:

  1. Sign up for the Slack Channel and Google Group.
  2. Please familiarize yourself with the Relevant Work.
  3. Create a new branch and then begin work on an open GitHub issue. Coordinate with others on Slack so that work is not duplicated unnecessarily.

The AI-ON process is experimental, but we will establish a review process for new code pull requests. We will seek to establish unit tests as well as performance tests on tasks as new modules are created.


We propose first investigating an extension to the Billiards task introduced in Sutskever et al. (2009)

Reinforcement Learning

We may simultaneously investigate the consciousness prior in the context of reinforcement learning, where the agent is in influencing the sensory input via control.