This module explains mathematical background of the most popular learning algorithm, called back propagation. It is widely used in multilayer perceptrons training but its usage is not limited to this particular type of neural network.
Surveys the molecular and cellular mechanisms of neuronal communication. Covers ion channels in excitable membrane, synaptic transmission, and synaptic plasticity. Correlates the properties of ion channels and synaptic transmission with their physiological function such as learning and memory. Discusses the organizational principles for the formation of functional neural networks at synaptic and cellular levels.
Life as an emergent property of networks of chemical reactions involving proteins and nucleic acids. Mathematical theories of metabolism, gene regulation, signal transduction, chemotaxis, excitability, motility, mitosis, development, and immunity. Applications to directed molecular evolution, DNA computing, and metabolic and genetic engineering.
Artificial Intelligence : Course lectures, hours 42. There are 11 pdf files, total 562 pages. Topics : Introduction to AI; Problem Solving - Search and Control Strategies; Knowledge Representation Issues - Predicate Logic, Rules; Reasoning System - Symbolic, Statistical; Game Playing; Learning; Expert System; Fundamentals of Neural Networks; Fundamentals of Genetic Algorithms; Natural Language Processing; Common Sense.
Introduces the theory and application of modern, computationally-based methods for exploring and drawing inferences from data. Covers re-sampling methods, non-parametric regression, prediction, and dimension reduction and clustering. Specific topics include Monte Carlo simulation, bootstrap cross-validation, splines, local weighted regression, CART, random forests, neural networks, support vector machines, and hierarchical clustering. De-emphasizes proofs and replaces them with extended discussion of interpretation of results and simulation and data analysis for illustration.
Presents the main concepts of decision analysis, artificial intelligence, and predictive model construction and evaluation in the specific context of medical applications. Emphasizes the advantages and disadvantages of using these methods in real-world systems and provides hands-on experience. Technical focus on decision analysis, knowledge-based systems (qualitative and quantitative), learning systems (including logistic regression, classification trees, neural networks), and techniques to evaluate the performance of such systems. Students produce a final project using the methods learned in the subject, based on actual clinical data. (Required for students in the Master's Program in Medical Informatics, but open to other graduate students and advanced undergraduates.)
Presents the main concepts of decision analysis, artificial intelligence, and predictive model construction and evaluation in the specific context of medical applications. Emphasizes the advantages and disadvantages of using these methods in real-world systems and provides hands-on experience. Technical focus on decision analysis, knowledge-based systems (qualitative and quantitative), learning systems (including logistic regression, classification trees, neural networks), and techniques to evaluate the performance of such systems. Students produce a final project using the methods learned in the subject, based on actual clinical data. (Required for students in the Master's Program in Medical Informatics, but open to other graduate students and advanced undergraduates.) From the course home page: It reviews computer-based diagnosis, planning and monitoring of therapeutic interventions. It also discusses implemented medical applications and the software tools used in their construction.
This series of research talks by members of the Department of Brain and Cognitive Sciences introduces students to different approaches to the study of the brain and mind. Topics include: "From Neurons to Neural Networks" "Prefrontal Cortex and the Neural Basis of Cognitive Control" "Hippocampal Memory Formation and the Role of Sleep" "The Formation of Internal Modes for Learning Motor Skills" "Look and See: How the Brain Selects Objects and Directs the Eyes" "How the Brain Wires Itself"
A survey of problems at the interface of statistical physics and modern biology: Bioinformatic methods for extracting information content of DNA; gene finding, sequence comparison, phylogenetic trees. Physical interactions responsible for structure of biopolymers; DNA double helix, secondary structure of RNA, elements of protein folding. Considerations of force, motion, and packaging; protein motors, membranes. Collective behavior of biological elements; cellular networks, neural networks, and evolution.
A survey of problems at the interface of statistical physics and modern biology: Bioinformatic methods for extracting information content of DNA; gene finding, sequence comparison, phylogenetic trees. Physical interactions responsible for structure of biopolymers; DNA double helix, secondary structure of RNA, elements of protein folding. Considerations of force, motion, and packaging; protein motors, membranes. Collective behavior of biological elements; cellular networks, neural networks, and evolution.
The main goal of this course is to study the generalization ability of a number of popular machine learning algorithms such as boosting, support vector machines and neural networks. Topics include Vapnik-Chervonenkis theory, concentration inequalities in product spaces, and other elements of empirical process theory.
The main goal of this course is to study the generalization ability of a number of popular machine learning algorithms such as boosting, support vector machines and neural networks. Topics include Vapnik-Chervonenkis theory, concentration inequalities in product spaces, and other elements of empirical process theory.
