Artificial Neural Networks

Overview

This course introduces fundamental concepts of artificial neural networks (ANN), encompassing deep feedforward networks, optimization and regularization techniques, hyperparameter adjustment, convolutional neural networks, object detection, recurrent neural networks, word embedding techniques, attention mechanisms/transformer models, and generative adversarial networks. Through hands-on exercises, students will explore the application of diverse ANN architectures across different data types, such as tabular data, images (spatial), sequential data (temporal), and graphs.

Recommended background: Linear algebra, Probability, Python.