A project intended to bring context to embodied computational agents. Layered brains from hybrid models!
https://github.com/Orthogonal-Research-Lab/Meta-brain-Models
Alicea, B. and Parent, J. (2022) Layers, Folds, and Semi-Neuronal Information Processing. Procedia Computer Science, 213, 443-452.
Alicea, B. and Parent, J. (2022). Meta-brain Models: biologically-inspired cognitive agents. International Workshop on Embodied Intelligence, IOP Conference Series: Materials Science and Engineering, 1261, 012019.
Alicea, B., Dvoretskii, S., Felder, S., Gong, Z., Gupta, A., and Parent, J. (2020). Developmental Embodied Agents as Meta-brain Models. Workshop on Developmental Neural Networks (DevoNN), Alife 2020 Conference.
Open-source contributor guide
Meta-brain models are hybrid models that include both a representation-free component and a representation-rich component. As we can see from the diagram above, this relationship mimics the neocortical-thalamic system relationship of the mammalian brain, and can be made spatially explicit (the representation-rich component can "encase" or be "layered" on top of the representation-free component).
Examples of a representation-free model includes Braitenberg Vehicles or Neural Networks. Examples of a representation-rich model (from our library) includes Contextual Geometric Structures or Ideological Connectionist models.
General References:
Brooks, R. (1991). Intelligence without Representation. Artificial Intelligence, 47, 139-159.
Cesario, J., Johnson, D.J., and Eisthen, H.L. (2020). Your Brain Is Not an Onion With a Tiny Reptile Inside. Current Directions in Psychological Science, 1–6.
Cisek, P. (2019). Resynthesizing behavior through phylogenetic refinement. Attention, Perception, and Psychophysics, 81, 2265-2287.
Hao, K. (2020). A debate between AI experts shows a battle over the technology’s future. MIT Technology Review, March 27.
Steels, L. (2003). Intelligence with representation. Philosophical Society A, 361, 2381–2395.
Wolff, M. and Vann, S.D. (2019). The Cognitive Thalamus as a Gateway to Mental Representations. Journal of Neuroscience, 39(1), 3-14. doi:10.1523/JNEUROSCI.0479-18.2018
Zhong, G., Wang, L-N., Xiao, X., and Dong, J. (2016). An overview on data representation learning: From traditional feature learning to recent deep learning. The Journal of Finance and Data Science, 2(4), 265-278.
Resources:
MAIN 2020 (hosted by Montreal AI-Neuro). YouTube
AI Debate II (hosted by Montreal AI). YouTube, TwirlyBird Notes
License CC-BY-SA 4.0 link
Presentations and Publications:
Meta-brain Models: biologically complex agent-based models. What AI can do for Agent-Based Modeling: Inverse Generative Social Science Workshop.