Introduction to classification and regression. Optimization, vectorization, gradient descent, cost, loss and activation functions. Introduction and basics to AI, Artificial Neural Networks, forward and backward propagation, Multi Layer Perceptron, and other types of Deep Neural Network models, their applications in multimedia, networks, finance, etc. Includes: Experiential Learning Activity Also listed as IRM 4005. Prerequisite(s): BIT 2000 and BIT 2400. Lectures three hours a week. [0.5 credits]
Introduction to classification and regression. Optimization, vectorization, gradient descent, cost, loss and activation functions. Introduction and basics to AI, Artificial Neural Networks, forward and backward propagation, Multi Layer Perceptron, and other types of Deep Neural Network models, their applications in multimedia, networks, finance, etc. Includes: Experiential Learning Activity Also listed as IRM 4005. Prerequisite(s): BIT 2000 and BIT 2400. Lectures three hours a week. [0.5 credits]
