Tag Archives: book

LM101-084: Ch6: How to Analyze the Behavior of Smart Dynamical Systems

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode of Learning Machines 101, we review Chapter 6 of my book “Statistical Machine Learning” which introduces methods for analyzing the behavior of machine inference algorithms and machine learning algorithms as dynamical systems. We show that when dynamical systems can be viewed as special types of optimization algorithms, the behavior of those systems even… Read More »

LM101-083: Ch5: How to Use Calculus to Design Learning Machines

Robot skier skiing on a mountain which symbolizes minimizing prediction error by gradient descent

Episode Summary: This particular podcast covers the material from Chapter 5 of my new book “Statistical Machine Learning: A unified framework” which is now available! The book chapter shows how matrix calculus is very useful for the analysis and design of both linear and nonlinear learning machines with lots of examples. Show Notes: Hello everyone! Welcome to the… Read More »

LM101-081: Ch3: How to Define Machine Learning (or at Least Try)

Android is equivalent to an iterated map whose dynamics are related to a preference relation

Podcast: Play in new window | Download | Embed

A large class of complex machine learning algorithms can be represented as dynamical systems which are minimizing an objective function with respect to a preference relation.

LM101-080: Ch2: How to Represent Knowledge using Set Theory

The purpose of the image is to illustrate the idea that we can represent concepts as subsets of a feature space.

Podcast: Play in new window | Download | Embed

Episode Summary: This particular podcast covers the material in Chapter 2 of my new book “Statistical Machine Learning: A unified framework” with expected publication date May 2020. In this episode we discuss Chapter 2 of my new book, which discusses how to represent knowledge using set theory notation. Chapter 2 is titled “Set Theory for Concept Modeling”. Show… Read More »

LM101-079: Ch1: How to View Learning as Risk Minimization

Android presenting his empirical risk family tree.

Podcast: Play in new window | Download | Embed

Episode Summary: This particular podcast covers the material in Chapter 1 of my new (unpublished) book “Statistical Machine Learning: A unified framework”. In this episode we discuss Chapter 1 of my new book, which shows how supervised, unsupervised, and reinforcement learning algorithms can be viewed as special cases of a general empirical risk minimization framework. This is useful… Read More »