Roadmap¶

Short-term¶

Debugged/consistent code on repository, then split release version from development branch.

Basic unit tests/benchmarks to compare with future versions.

Configuration script: set local paths.

Develop a programmable model, allowing user to specify structure of model.

• Determine order in which distributions are combined.
• Specify weights for particular combinations, e.g. weighted viewpoints, or weighted memory stores.
• Multiple memory stores.
• Specify alternative context strategies.
• Provide some

Mid-term¶

• Allow models to use predictive information (PI), expected PI and PI rate (as analogs to IC, entropy and entropy rate respectively).
• Feature selection/generation.

Long-term¶

• Hierarchical structure?
• Parallel implementations?