Bayesian Deep Learning (CS-0145)

Spring 2026 · CS 0145 · Tufts University · 3 credits · Undergraduate

Modern deep learning methods (scalable gradient-based training of flexible neural networks for regression and classification) and modern Bayesian statistical methods. Estimating probabilities and making decisions under uncertainty, using these methods. Modeling innovations (e.g., models for functions and deep generative models), learning paradigms (e.g. MCMC and variational inference), and probabilistic programming platforms (e.g., JAX, PyTorch, Tensorflow, PyMC3). Coding exercises, student-led discussion of recent literature, and a long-term self-designed research project. Designing, implementing, and evaluating new contributions in this exciting research space.

Course codes: CS-0145, CS 0145, CS0145, CS-145, CS 145, CS145

Course Discovery