The primary objective of this course is to explore the synthetic modeling approach to understand brain-based mechanisms for learning and generating sensory-motor behaviors. For this purpose, the course will offer introduction of neuro-robotics studies as well as neuroscience literature related to brain mechanisms for sensory perception and behavior generation. In addition, the course will offer hands-on experiences on experimenting neuro-driven learnable robots in the instructor’s lab. The course will gain a good understanding of mechanisms for learning and generating cognitive behaviors both in biological brains and artifacts. Evaluation is based on quizzes during class, term project, and active class participation.
Introduce students the fundamental concepts and intuition behind modern machine learning techniques and algorithms, beginning with topics such as perceptron to more recent topics such as boosting, support vector machines and Bayesian networks. Statistical inference will be the foundation for most of the algorithms covered in the course.
This course will discuss the key differences in architecture and algorithms between conventional information processing systems (e.g. von Neumann machines) and biological brains. Subsequently, we will try to come up with the scaffold of a basic design for a non-von Neumann type of brain-like information processing system.
This course covers the theory and application of neural networks. In particular, lectures explore the structure and function of neural networks and their learning and generalization. Also, various models of neural networks and their applications are illustrated.