Foundations – Engineering AI Agents

Author

Pantelis Monogioudis

The Learning Problem

Statistical Learning Theory

The supervised learning problem statement.

Optimization Algorithms

In this section we close the circle that will allow us to train a model - we need an algorithm that will help us search efficiently in the weight space the optimal vector \(\…

Maximum Likelihood Estimation of Gaussian Parameters

This text appearred in this post but because the math formatting disappeared from the original site, it is shamelessly copied here. Please note that in our notation \(N\) is …

Introduction to Classification

There are three broad classes of methods for determining the parameters \(\mathbf{w}\) of a linear classifier:

The Neuron (Perceptron)

Frank Rosenblatt

Logistic Regression

Logistic regression is used in machine learning extensively - every time we need to provide probabilistic semantics to an outcome e.g. predicting the risk of developing a…

AI Agents

We will cover the agent-environment interface, the rational, learning agent architectures and a practical example of a robotic agent.

Pantelis Monogioudis

The four approaches towards AI

Ultimately AI will be a cloud of reasoning systems.

Pantelis Monogioudis

Entropy

Information Theory

We will cover the value of information, the entropy of a probability distribution and the cross-entropy between two probability distributions.

Pantelis Monogioudis