This course covers the learning outcomes and goals of deep probabilistic modeling using Pyro. Students will learn how to appropriately model uncertain knowledge and reasoning to make better decisions. The course teaches skills such as probabilistic and deep probabilistic modeling, Pyro framework, Bayesian networks, Gaussian processes, and probabilistic programming languages. The teaching method involves a combination of theoretical concepts and real-world examples. The intended audience for this course includes individuals interested in machine learning, deep learning, probabilistic modeling, and Pyro framework.
Overview
Syllabus
Intro
Time Series Prediction
Multi-Sensor Systems
Deep Neural Networks - Limitations
Adversarial Attacks
Neural Networks Predictions
Neural Networks Bias
Conditional Probability
Inference from Data
Probabilistic Regression
Bayes Networks
Gaussian Processes
Probabilistic Neural Networks
Probabilistic Programming Languages
Pyro - Framework
Pyro/Py Torch Example: MNIST
Neural Network Softmax Prediction
Pyro: Weight Priors
Pyro: Inference
Pyro: Variational Inference
Pyro: Loss & Training
Pyro: Sampling from the posterior
Random Noise
Predictive Maintenance Example
Sensor Data 1
Neural Network Prediction
Summary
Taught by
MLCon | Machine Learning Conference
