This class will introduce fundamentals of machine learning techniques and deep dive in cutting edge concepts that enabled neural networks to achieve state of the art performance in many visual, textual, and biomedical problems. Fundamental concepts like feed forward networks, convolution networks, recurrent neural networks, back propagation, loss functions, batch gradient descent, and stochastic optimization will be studied.
Learning Objectives
Describe the fundamental concepts in machine learning, and the reasons behind the rise of neural networks to scale with today’s big datasets. Formulate machine learning problems and identify suitable neural networks models to solve them. Use modern neural networks frameworks (e.g., Keras, TensorFlow, PyTorch) to train, validate, test, and debug state of the art models. Address challenges, identify solutions, and explore opportunities in using neural networks in various application domains.
Framework Connections
The materials within this course focus on the NICE Framework Task, Knowledge, and Skill statements identified within the indicated NICE Framework component(s):