Architecture
One of the objectives of WBAI and the WBAI Hackathons is to promote the development of functional brain models that exploit knowledge about the architecture of animal brains. We hope this will lead to further discoveries in AI, Machine Learning and computational neuroscience.
This hackathon is on the topic of Working Memory (WM). For some introduction to the topic of WM see our resources. While the mechanism of working memory has not been completely elucidated, the following might be said:
- Since working memory is involved in perceptual representation, sensory areas (neocortices other than the frontal area) are involved. The content of working memory (perceptual content of the past) and the present perceptual content must be distinguished within the cortex.
- Since the working memory is involved in the executive function by definition, the frontal lobe, which is supposed to be involved in the executive function, is involved.
- Thus, working memory involves a network between the frontal lobe and the sensory cortices. The executive function (frontal lobe) controls the retention and termination of working memory by interacting with the perceptual areas.
We are planning to provide the following reference architecture for the 5th WBA Hackathon, which modelathon participants are encouraged but not obliged to use. It is not necessary to elaborate all components for the hackathon.
WBAI proposes the Brain Information Flow Diagram (BIF) as a format for describing and sharing whole brain architecture. Modelathon participants are requested to submit the model in BIF (spreadsheet format). The BIF of the reference architecture is found here.
The reference architecture above has been implemented in code. A number of frameworks have been used including PyGame for implementing gameplay, RLLib (for Reinforcement Learning) and PyTorch (for Machine Learning models). The codebase is illustrated from different perspectives below showing:
- Software stack / Inheritance hierarchy
- Architecture diagram
