 |
Fall 1998 Courses |
| This page last updated 3 March 1999 | |
|
Fall 1998 Courses |
| This page last updated 3 March 1999 | |
Machine Learning is concerned with computer programs that automatically improve their performance through experience. This course covers the theory and practice of machine learning from a variety of perspectives. We cover topics such as learning decision trees, neural network learning, statistical learning methods, genetic algorithms, Bayesian learning methods, explanation-based learning, and reinforcement learning. The course covers theoretical concepts such as inductive bias, the PAC and Mistake-bound learning frameworks, minimum description length principle, and Occam's Razor. Programming assignments include hands-on experiments with various learning algorithms. Typical assignments include neural network learning for face recognition, and decision tree learning from databases of credit records.
An introduction to the theory and practice of computer vision, i.e. the analysis of the patterns in visual images of the world with the goal of reconstructing the objects and processes in the world that are producing them. This includes the ``low-level'' algorithms of image processing, multi-scale analysis, segmentation of images, correspondence of multiple images and reconstruction of depth. It continues with ``high-level'' algorithms of pattern recognition and the analysis and recognition of shapes, objects and scenes using feature, templates and models. The discussion will be guided by comparison with human and animal vision, from psychological and biological perspectives.
This course will cover fudamental findings and approaches in cognitive neuroscience, with the goal of providing an overview of the field at an advanced level. Topics will include high-level vision, spatial cognition, working memory, long-term memory, learning, language, executive control, and emotion. Each topic will be appraoched from a variety of methodological directions, i.e. computational modeling, cognitive assessment in brain-damaed humans, non-invasive brain monitoring in humans and single-neuron recording in animals. Lecture format will be used for most sessions, with a few sessions devoted to discussion.The class will meet at 10:30-12 Tuesday and Thursday in the CNBC Conference Room, 115 Mellon Institute. Carl Olson and Jay McClelland are the instructors as before. The course is taught at a graduate level, and requires in-depth critical analysis of experimental and theoretical arguments as presented in primary research publications. [For undergraduates, permission of instructor (McClelland or Olson) is required: Undergraduates will only be admitted if their skills and preparation are comparable to what we expect of first-year graduate students.]
IMPORTANT: The course will be taught according to the PITT SCHEDULE, which means that the first class will not occur until Tuesday, Sept 1. The last class will occur on Thurday Dec 10, which is during the CMU
The structure and expression of eukaryotic genes are discussed, focusing on model systems from a variety of organisms. Current topics discussed include (1) isolation of specific DNA sequences using recombinant DNA technology, (2) the control of gene expression at the level of transcription, splicing and translation, (3) chromosome structure, including origins of replication, centromeres, telomeres, and transposons, and (4) molecular biology of humans. 4 hrs. lec. Prerequisite: 03-441 or instructor's permission.
This is the first of three introductory graduate courses designed to provide an overview of neuroscience. The topics covered include the electrophysiology of resting and action potentials, the electrophysiological analysis of synaptic transmission, and the modeling of small neural networks.
This is the second in the introductory graduate series of courses designed to provide an overview of neuroscience. Much of the course is devoted to the biochemical basis of chemical synaptic transmission, with an emphasis on regulatory mechanisms.
This course will cover fudamental findings and approaches in cognitive neuroscience, with the goal of providing an overview of the field at an advanced level. Topics will include high-level vision, spatial cognition, working memory, long-term memory, learning, language, executive control, and emotion. Each topic will be appraoched from a variety of methodological directions, i.e. computational modeling, cognitive assessment in brain-damaed humans, non-invasive brain monitoring in humans and single-neuron recording in animals. Lecture format will be used for most sessions, with a few sessions devoted to discussion.
This course covers the basic structure of the central nervous system from spinal cord to cerebral cortex. The major sensory, motor and integrative neural systems of the human brain are discussed. Based on an understanding of normal neural connections and brain function, the anatomical and physiological basis of various neurological disorders of the nervous system will be explored.
This course is an introduction to the psychology of language. The focus is on language as a cognitive process. The central questions concern how humans understand and produce language, both spoken and written. Topics include language comprehension, meaning, speech production, conversations, language structure, linguistic relativity, and reading and writing systems. A lecture-discussion format is used.
This class provides an overview to the study of human memory. Following a brief review of historical approaches to the study of learning and memory, the course reviews current issues in memory including: sensory memory, working memory, long-term memory, encoding and retrieval processes, memory models, eyewitness memory and autobiographical memory. The course attempts to provide a balance between empirical and theoretical approaches, as well as considering both laboratory and real world research methods.
This seminar course is for students interested in the electrophysiology of synaptic computation. It will cover mechanisms of transmitter release and transmitter action with an eye toward consequences for neural circuit function. Readings will emphasize experiments at the cellular level using contemporary biophysical, molecular and imaging techniques. Students will participate in weekly discussions of original papers and relevant reviews, and will write a paper that reviews a research problem.
Introduces mathematical and computer techniques used in constructing models of information processing by parallel distributed processing (PDP) networks; principles of input-output functions and adaptation (learning) functions in single units and in networks; the relation between PDP networks, neurobiology, artificial inteligence, and cognition.
This seminar course will examine the role of the cerebral cortex in perceptual/motor functions. Topics include cortical columnar organization, feature detection, population coding, dynamic receptive field properties, local circuits and mutliple representations. Students will read primary source articles as well as some theoretical monographs. There will be no formal lectures or student presentations. Grades are based on class participation and a final paper. Class size is limited, and permission of the instructor is required. The class will meet once per week, preferably on Mondays, at a time to be determined. Contact Dr. Simons at 648-9442 or cortex+@pitt.edu.
1. This course will introduce the student to new concepts from dynamical systems. Invariant manifolds, normal forms; bifurcations & chaos will be discussed from the geometric point of view. Some global analysis will also be described. Numerical tools and methods for analyzing local bifurcations will also be discussed. Emphasis will be on practical applications of these techniques.2. Prerequisites: Linear algebra and a course in differential equations at the upper undergraduate level. Some familiarity with analysis.
4. Expected Class Size: 10-15 students. 5. This course is being offered for the first time.
Top of Page \ Current Classes \ Training \ CNBC Home Page \ Page Credits \ Comments \ Search