A313
Course Coordinator:
Jun Tani
Cognitive Neurorobotics
Description:
Explore the principles of embodied cognition by a synthetic neurorobotics modeling approach in combination with hands-on neurorobotics experiments and related term projects. Combine related interdisciplinary findings in artificial intelligence and robotics, phenomenology, cognitive neuroscience, psychology, and deep and dynamic neural network models. Perform neurorobotics simulations and control experiments with extensive coding in C++ or Python. Critically analyze and report on recent papers in neurorobotics and artificial intelligence.
Aim:
This course aims to provide an overview of the synthetic approach to understand embodied cognition by using deep dynamic neural network models and robotics platforms.
Course Content:
- Introduction: cognitive neurorobotics study
- Cognitism: compositionality and symbol grounding problem
- Phenomenology: consciousness, free will and embodied minds
- Cognitive neuroscience I: hierarchy in brains for perception and action
- Cognitive neuroscience II: Integrating perception and action via top-down and bottom-up interaction
- Affordance and developmental psychology
- Nonlinear dynamical systems I: Discrete time system
- Nonlinear dynamical systems II: Continuous time system
- Neural network model I: 3-layered perceptron, recurrent neural network
- Neural network model II: deep learning, variational Bayes
- Neurorobotics I: affordance & motor schema
- Neurorobotics II: higher-order cognition, meta-cognition, and consciousness
- Neurorobotics III: hands-on experiments in lab
- Paper reading for neurorobotics and embodied cognition I
- Paper reading for neurorobotics and embodied cognition II
Course Type:
Elective
Credits:
2
Assessment:
Mid-term exam: 40%, final term project report: 60%.
Text Book:
- Exploring robotic minds: actions, symbols, and consciousness as self-organizing dynamic phenomena. Jun Tani (2016) Oxford University Press.
Reference Book:
Prior Knowledge:
Basic mathematical knowledge for the calculus of vectors and matrices and the concept of differential equations are assumed.
B46 Introduction to Machine Learning (or similar) and programming experience in Python, C or C++ are required.
Notes: