Lecture Series: Predictive Modeling and Learning

This lecture series provides an introductory course to basic notions of artificial intelligence, modeling of agents, and learning. It comprises three main parts, namely

  • Part A: Introduction to Artificial Intelligence
  • Part B: Modeling and Probabilistic Reasoning
  • Part C: Learning Probabilistic Models

Our focus is primarily on basic forms of predictive models. In particular, we focus on two different classes of predictive models, namely probabilistic models (such as causal inference models) and linear estimation models. In the former case, we also explore the use of hidden variables that we could also assist in the detection and estimation of unobserved events.

Part A: Introduction to Artificial Intelligence

This part of the lecture series provides an introduction to Artificial Intelligence and its core elements, such as the notion of the “agent” as well as its different types (e.g., the model-based agent presented in the following figure).

Figure 1. Model-based Agent

Subscribe to get full access to all lectures

Read more of this content when you subscribe today.

Subscribe

Part B: Modeling and Probabilistic Reasoning

This part of the lecture series comprises six lectures, including Probabilistic Reasoning and Exact Inference, Probabilistic Reasoning over Time (Part A and B), and Linear Models (Part A and B).

Figure 2. Sample graph indicating conditional probability dependencies in an alarm system.

Subscribe to get full access to all lectures

Read more of this content when you subscribe today.

  • Lecture 5: Quantifying Uncertainty (Probability Background)
  • Lecture 6: Probabilistic Reasoning: Bayesian Networks and Exact Inference
  • Lecture 7: Probabilistic Reasoning over Time (Part A)
  • Homework 2
  • Lecture 8: Probabilistic Reasoning over Time (Part B)
  • Lecture 9: Linear Models (Part A)
  • Lecture 10: Linear Models (Part B)
  • Homework 3

Subscribe

Part C: Learning Probabilistic Models

This part of the lecture series provides an introduction to Learning Probabilistic Models.

Figure 3. Example of Bayesian network with a hidden variable and unknown learning parameters.

Subscribe to get full access to all lectures

Subscribe

Blog at WordPress.com.

Up ↑