As of 2021, the Department of Mathematics and Statistics and the Department of Physics and Astronomy have been combined into the Mathematics, Physics, Astronomy and Statistics Department.
Other News and Announcements
MATH 4890/5890 – ONLINE
Introduction to Artificial Neural Networks
Instructor: Adrian Clingher
Course Overview: In recent years, artificial neural networks have dramatically advanced the capabilities of computers to perform specialized tasks, such as image classification and processing, speech and handwriting recognition, medical data analysis, autonomous car navigation, fraud detection, natural language processing, game playing, and many others. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas and are widely deployed in industry, academia and government applications. This course introduces students to the mathematical ideas and techniques underlying artificial neural network models. Students will receive training and guidance that will teach them how and where this technology is currently being implemented and will think critically about future applications. Course topics may include: basics of supervised learning, loss functions, regularization, gradient descent optimization, feed forward neural networks, forward propagation, activation functions, cross-entropy loss, back propagation algorithm, convolutional neural networks, building blocks, training, specialized architecture. The API Keras, via an R interface, will be used as computing environment.
Prerequisites: Basic statistics (Math 1320 or equivalent), multi-variable calculus (Math 2000 or equivalent), elementary linear algebra (Math 2450 or equivalent) or consent of the instructor. No prior programming experience is assumed.
Questions? Send an email to the instructor at firstname.lastname@example.org