Learning Machines 101

In this rerun of Episode 10, we discuss fundamental principles of learning in statistical environments including the design of learning machines that can use prior knowledge to facilitate and guide the learning of statistical regularities. The topics of ML (Maximum Likelihood) and MAP (Maximum A Posteriori) estimation are discussed in the context of the nature versus nature problem.

Check out: www.learningmachines101.com to obtain transcripts of this podcastand access to free machine learning software!

In this episode we consider the problem of learning when the actions of the learning machine can alter the characteristics of the learning machine’s statistical environment. We illustrate the solution to this problem by designing an autopilot for a lunar lander module that learns from its experiences!

Check out: www.learningmachines101.com to obtain transcripts of this podcast and download free machine learning software!

In this episode we introduce the concept of learning machines that can self-evolve using simulated natural evolution into more intelligent machines using Monte Carlo Markov Chain Genetic Algorithms. Check out:

www.learningmachines101.com

to obtain transcripts of this podcast and download free machine learning software!

Recently, there has been a lot of discussion and controversy over the currently hot topic of “deep learning”!! Deep Learning technology has made real and important fundamental contributions to the development of machine learning algorithms. Learn more about the essential ideas of "Deep Learning" in Episode 23 of "Learning Machines 101". Check us out at our official website: www.learningmachines101.com !

In this episode we discuss how to learn to solve constraint satisfaction inference problems. The goal of the inference process is to infer the most probable values for unobservable variables. These constraints, however, can be learned from experience. At the end of the episode, we discuss one (unproven) theory from the field of neuroscience that our "dreams" are actually neural simulations of variations of events we have experienced during the day and "unlearning" of these dreams helps us to organize our memory!

Visit us at: www.learningmachines101.com to obtain additional references, make suggestions regarding topics for future podcast episodes by joining the learning machines 101 community, and download free machine learning software!

We discuss how to solve constraint satisfaction inference problems where knowledge is represented as a large unordered collection of complicated probabilistic constraints among a collection of variables. The goal of the inference process is to infer the most probable values of the unobservable variables given the observable variables.

Please visit: www.learningmachines101.com to obtain transcripts of this podcast and download free machine learning software!

In this episode we introduce some advanced nonlinear machine software which is more complex and powerful than the linear machine software introduced in Episode 13. Specifically, the software implements a multilayer nonlinear learning machine, however, whose inputs feed into hidden units which in turn feed into output units has the potential to learn a much larger class of statistical environments. Download the free software from: www.learningmachines101.com now!

Embodied cognition emphasizes the design of complex artificially intelligent systems may be both vastly simplified and vastly enhanced if we view the robotic bodies of artificially intelligent systems as important contributors to intelligent behavior.

Check out: www.learningmachines101.com to obtain transcripts of this podcast and download free machine learning software!

In this episode, we explore the question of what can computers do as well as what computers can’t do using the Turing Machine argument. Specifically, we discuss the computational limits of computers and raise the question of whether such limits pertain to biological brains and other non-standard computing machines.

This is a rerun of Episode 4. We continue new podcasts in January 2015!

For a transcript of this episode, please visit our website: www.learningmachines101.com!!!

This episode we discuss the Turing Test for Artificial Intelligence which is designed to determine if the behavior of a computer is indistinguishable from the behavior of a thinking human being. The chatbot A.L.I.C.E. (Artificial Linguistic Internet Computer Entity) is interviewed and basic concepts of AIML (Artificial Intelligence Markup Language) are introduced.