| |
Mar 14, 2026
|
|
|
|
|
CSC 6621 - Applied Machine Learning4 lecture hours 0 lab hours 4 credits
Course Description
This course expands on the introduction to data science and machine learning in CSC 5610 with coverage of deep learning applied to non-tabular data such as images, text, and other forms of sequential data. Students will be introduced to deep learning libraries, architectures, and concepts such as loss functions, backpropagation, and optimization algorithms. Students will participate in a seminar-like experience where primary literature is read and presented. A final project will allow students to explore topics and applications beyond those presented in class. Students will reinforce their understanding of deep learning with hands-on laboratory exercises for development of representative applications.
Prereq: (CSC 5610 or CSC 2621) and (MTH 2130, MTH 2340, MTH 2810, or MTH 5810 ) or instructor consent
Note: None
Course Learning Outcomes
Upon successful completion of this course, the student will be able to:
- Assess experimental designs for evaluating machine learning models on complex data sets, including issues such as data leakage
- Choose appropriate modern deep neural network architectures, such as dense neural networks, CNNs, encoder-decoders, GANs, and transformers, for a given problem
- Apply deep learning models to real-world problems and applications
- Use popular deep learning libraries and frameworks to train, evaluate, and apply deep learning models
- Apply and fine-tune pretrained deep learning models for a given problem
- Identify and mitigate challenges such as underfitting, overfitting, and vanishing and exploding gradients.
- Compare data size and computational resource requirement tradeoffs of deep learning versus classical machine learning
- Read, summarize, and present academic papers from the field of machine learning
- Present results of machine learning projects to technical audiences
Prerequisites by Topic
- Software development
- Object-oriented Python
- Jupyter Notebooks
- Data ingestion, manipulation, and cleaning using DataFrames
- Data exploration and interpretation using visualization and statistical techniques
- Training, evaluating, and applying classical machine learning models
- Ability to apply and interpret appropriate metrics for classification and regression problems
Coordinator
Dr. Sebastian Berisha
Add to Portfolio (opens a new window)
|
|
Skip to Main Content
