CSCI 325 - Deep Learning

3 Credits
This course will introduce the student to the theory and application of deep learning. Machine learning concepts will be covered such as hyperparameters, validation sets, overfitting, under-fitting, bias and variance. Methods for regularization of deep learning methods will be discussed as well as the optimization and application of deep learning algorithms to real world problems. Other concepts that may be discussed could include convolutional networks and autoencoders.

Fees: Additional course fees apply.
Prerequisite(s): CSCI 280
Course Learning Outcomes:
1. Evaluate deep learning methods to solve a given problem.
2. Analyze the theoretical foundations intrinsic in deep learning algorithms.
3. Select the appropriate methods to tune a deep learning network selecting the appropriate methods.
4. Identify key architectural components of deep networks.
5. Describe the effect of numerical computation and optimization on a deep learning algorithm.