STSCI 4720

Applied Neural Networks

Course Description

Course information provided by the 2025-2026 Catalog.

Neural networks form the backbone of modern artificial intelligence methodologies. This course will survey various neural networks architectures with a heavy emphasis on practical application to their specific data use cases. Students will explore how neural networks generalize classical statistical models and function estimation techniques, and how statistical principles inform model design, optimization, and evaluation. Topics include feedforward architectures, stochastic gradient descent, regularization and model selection, convolutional and recurrent networks, and an introduction to attention-based models.

Prerequisites An introductory course in statistics and python programming experience.

Last 4 Terms Offered (None)

Learning Outcomes

• Demonstrate a practical working knowledge of neural network architectures.
• Interpret neural network outputs using sensitivity and diagnostic tools.
• Evaluate model complexity and performance through regularization, cross-validation, and bias–variance analysis.
• Produce quantitative analyses of data in Python through the implementation of neural networks using PyTorch.

View Enrollment Information