CBMM faculty offer graduate and undergraduate courses that integrate computational and empirical approaches used in the study of problems related to intelligence. These courses introduce some of the mathematical frameworks used to formulate computational models, and experimental methods used in the fields of neuroscience and cognitive science to study the neural implementations of intelligent processes and manifestation of these computations in human cognitive behavior. Examples of the integration of these perspectives are drawn from current research on intelligence. Materials for many of these courses are available online. Most graduate courses are open to advanced undergraduates with appropriate background. Enrollment for courses is handled through the respective institutions.

Fall 2017

Massachusetts Institute of Technology (MIT)

Science of Intelligence
Explores the problem of intelligence - its nature, how it is produced by the brain and how it could be replicated in machines - with an approach that integrates computational modeling, neuroscience and cognitive science. Focuses on four intellectual thrusts: how intelligence is grounded in computation, how these computations develop in childhood, how they are implemented in neural systems, and how social interaction enhances these computations. Research within these thrusts is integrated through an overarching theme of how they contribute to a computational account of how humans analyze dynamic visual imagery to understand objects and actions in the world.
Statistical Learning Theory and Applications
Provides students with the knowledge needed to use and develop advanced machine learning solutions to challenging problems. Covers foundations and recent advances of machine learning in the framework of statistical learning theory. Focuses on regularization techniques key to high-dimensional supervised learning. Starting from classical methods such as regularization networks and support vector machines, addresses state-of-the-art techniques based on principles such as geometry or sparsity, and discusses a variety of algorithms for supervised learning, feature selection, structured prediction, and multitask learning. Also focuses on unsupervised learning of data representations, with an emphasis on hierarchical (deep) architectures.
Computational Cognitive Science
Introduction to computational theories of human cognition. Focuses on principles of inductive learning and inference, and the representation of knowledge. Computational frameworks include Bayesian and hierarchical Bayesian models, probabilistic graphical models, nonparametric statistical models and the Bayesian Occam's razor, sampling algorithms for approximate learning and inference, and probabilistic models defined over structured representations such as first-order logic, grammars, or relational schemas. Applications to understanding core aspects of cognition, such as concept learning and categorization, causal reasoning, theory formation, language acquisition, and social inference.
Principles of Neuroengineering
Covers how to innovate technologies for brain analysis and engineering, for accelerating the basic understanding of the brain, and leading to new therapeutic insight and inventions. Focuses on using physical, chemical and biological principles to understand technology design criteria governing ability to observe and alter brain structure and function. Topics include optogenetics, noninvasive brain imaging and stimulation, nanotechnologies, stem cells and tissue engineering, and advanced molecular and structural imaging technologies. Design projects by students.
Artificial Intelligence
Introduces representations, techniques, and architectures used to build applied systems and to account for intelligence from a computational point of view. Applications of rule chaining, heuristic search, constraint propagation, constrained search, inheritance, and other problem-solving paradigms. Applications of identification trees, neural nets, genetic algorithms, and other learning paradigms. Speculations on the contributions of human vision and language systems to human intelligence.
Neuroscience of Morality
Advanced seminar that covers both classic and cutting-edge primary literature from psychology and the neuroscience of morality. Addresses questions about how the human brain decides which actions are morally right or wrong (including neural mechanisms of empathy and self-control), how such brain systems develop over childhood and differ across individuals and cultures, and how they are affected by brain diseases (such as psychopathy, autism, tumors, or addiction). Instruction and practice in written and oral communication provided. Limited to 24.

University of Central Florida

Course Description: Lecture and workshop series on introductory topics related to Artificial Intelligence. Each unit in the series consists of lectures on the topic and then workshops focused on building the systems covered in the lecture(s). Topics include neural networks, reinforcement learning, [neuro]evolutionary computation, and building machines that learn and think like people.

Stanford University

Computation and Cognition: The Probabilistic Approach
This course introduces the probabilistic approach to cognitive science, in which learning and reasoning are understood as inference in complex probabilistic models. Examples are drawn from areas including concept learning, causal reasoning, social cognition, and language understanding. Formal modeling ideas and techniques are discussed in concert with relevant empirical phenomena.

Harvard University

Visual Object Recognition: Computational and Biological Mechanisms
Visual recognition is essential for most everyday tasks including navigation, reading and socialization, and is also important for engineering applications such as automatic analysis of clinical images, face recognition by computers, security tasks and automatic navigation. In spite of the enormous increase in computational power over the last decade, humans still outperform the most sophisticated engineering algorithms in visual recognition tasks. This course examines how circuits of neurons in visual cortex represent and transform visual information, covering the following topics: functional architecture of visual cortex, lesion studies, physiological experiments in humans and animals, visual consciousness, computational models of visual object recognition, computer vision algorithms.

Johns Hopkins University

Probabilistic Models of the Visual Cortex
The course gives an introduction to computational models of the mammalian visual cortex. It covers topics in low-, mid-, and high-level vision. It briefly discusses the relevant evidence from anatomy, electrophysiology, imaging (e.g., fMRI), and psychophysics. It concentrates on mathematical modelling of these phenomena taking into account recent progress in probabilistic models of computer vision and developments in machine learning, such as deep networks.