INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS

Prerequisites & course information

Requisites: COMP SCI 200 , 220 , 300 , 301, 310 , placement into COMP SCI 300 , or graduate/professional standing Course Designation: Level - Advanced L&S Credit - L&S Liberal Arts and Science Repeatable for Credit: No Last Taught: Fall 2026 Learning Outcomes: 1. Identify if a given data analysis task is a pattern classification problem or a model approximation problem. Audience: Undergraduate 2. Apply multi-layer perceptron neural network training algorithm to develop artificial neural network (ANN) based pattern classifiers and data predictors. Audience: Undergraduate 3. Apply deep learning network for pattern classification Audience: Undergraduate 4. Apply support vector machine (SVM) to develop pattern classifiers. Audience: Undergraduate 5. Apply self-organization map and k-means to perform clustering operations of a given data set. Audience: Undergraduate 6. Apply stochastic optimization methods, including simulated annealing, genetic algorithm and random search to solve a discrete optimization problem. Audience: Undergraduate Learning Outcomes: 1. Identify if a given data analysis task is a pattern classification problem or a model approximation problem. Audience: Undergraduate 2. Apply multi-layer perceptron neural network training algorithm to develop artificial neural network (ANN) based pattern classifiers and data predictors. Audience: Undergraduate 3. Apply deep learning network for pattern classification Audience: Undergraduate 4. Apply support vector machine (SVM) to develop pattern classifiers. Audience: Undergraduate 5. Apply self-organization map and k-means to perform clustering operations of a given data set. Audience: Undergraduate 6. Apply stochastic optimization methods, including simulated annealing, genetic algorithm and random search to solve a discrete optimization problem. Audience: Undergraduate