LM101-036: How to Predict the Future from the Distant Past using Recurrent Neural Networks

Elman or Simple Recurrent Neural Network (RNN) with a robot looking into the future using a crystal ball.

Podcast: Play in new window | Download | Embed

LM101-036: How to Predict the Future from the Distant Past using Recurrent Neural Networks Episode Summary: In this episode, we discuss the problem of predicting the future from not only recent events but also from the distant past using Recurrent Neural Networks (RNNs). A example RNN is described which learns to label images with simple sentences. A learning… Read More »

LM101-035: What is a Neural Network and What is a Hot Dog?

Robot with neural network processor trying to decide which image best represents a "hot dog".

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode, we address the important questions of “What is a neural network?” and “What is a hot dog?” by discussing human brains, neural networks that learn to play Atari video games, and rat brain neural networks. Show Notes: Hello everyone! Welcome to the thirty-fifth podcast in the podcast series Learning Machines 101. In this… Read More »

LM101-034: How to Use Nonlinear Machine Learning Software to Make Predictions (Feedforward Perceptrons with Radial Basis Functions)[Rerun]

Gaussian mixture model and multilayer radial basis function machine learning software.

Podcast: Play in new window | Download | Embed

LM101-034: How to Use Nonlinear Machine Learning Software to Make Predictions (Feedforward Perceptrons with Radial Basis Functions)[Rerun] Episode Summary: In this episode we describe how to download and use free nonlinear machine learning software which is more advanced than the linear machine software introduced in Episode 13. Show Notes: Welcome to the 34th podcast in the podcast series… Read More »

LM101-033: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software)[RERUN]

Free Linear Regression Software Download

Podcast: Play in new window | Download | Embed

LM101-033: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software)[RERUN]   Episode Summary: In this episode we describe how to download and use free linear machine learning software to make predictions for classifying flower species using a famous machine learning data set. This is a RERUN of Episode 13. Show Notes: Hello everyone! Welcome… Read More »

LM101-032: How To Build a Support Vector Machine to Classify Patterns

Robot thinking about how to classify letters.

Podcast: Play in new window | Download | Embed

LM101-032: How To Build a Support Vector Machine to Classify Patterns Episode Summary: In this 32nd episode of Learning Machines 101, we introduce the concept of a Support Vector Machine. We explain how to estimate the parameters of such machines to classify a pattern vector as a member of one of two categories as well as identify special… Read More »

LM101-031: How to Analyze and Design Learning Rules using Gradient Descent Methods (RERUN)

Android robot skis downhill.

Podcast: Play in new window | Download | Embed

LM101-031: How to Analyze and Design Learning Rules using Gradient Descent Methods (RERUN) Episode Summary: In this episode we introduce the concept of gradient descent which is the fundamental principle underlying learning in the majority of machine learning algorithms. Show Notes: Hello everyone! Welcome to the sixteenth podcast in the podcast series Learning Machines 101. In this series… Read More »

LM101-030: How to Improve Deep Learning Performance with Artificial Brain Damage (Dropout and Model Averaging)

What robot is thinking when it classifies a dog image as the word dog.

Podcast: Play in new window | Download | Embed

LM101-030: How to Improve Deep Learning Performance with Artificial Brain Damage (Dropout and Model Averaging) Episode Summary: Deep learning machine technology has rapidly developed over the past five years due in part to a variety of factors such as: better technology, convolutional net algorithms, rectified linear units, and a relatively new learning strategy called “dropout” in which hidden… Read More »

LM101-029: How to Modernize Deep Learning with Rectilinear units, Convolutional Nets, and Max-Pooling

Deep learning neural network is projected on projection screen.

Podcast: Play in new window | Download | Embed

LM101-029: How to Modernize Deep Learning  with Rectilinear units,  Convolutional Nets, and Max-Pooling Episode Summary This podcast discusses the topics of rectilinear units, convolutional nets, and max-pooling relevant to deep learning which were inspired by my recent visit to the 3rd International Conference on Learning Representations (May 7-9, 2015) in San Diego. Specifically, commonly used techniques shared by… Read More »

LM101-028: How to Evaluate the Ability to Generalize from Experience (Cross-Validation Methods)[RERUN]

There is no correct interpretation of the identity of an ambiguous letter.

Podcast: Play in new window | Download | Embed

LM101-028: How to Evaluate the Ability to Generalize from Experience (Cross-Validation Methods)[RERUN] Episode Summary: In this episode we discuss the problem of how to evaluate the ability of a learning machine to make generalizations and construct abstractions given the learning machine is provided a finite limited collection of experiences. Show Notes: Hello everyone! Welcome to a RERUN of… Read More »

LM101-027: How to Learn About Rare and Unseen Events (Smoothing Probabilistic Laws)[RERUN]

How do you compute the probability of rare and unseen events?

Podcast: Play in new window | Download | Embed

LM101-027: How to Learn About Rare and Unseen Events (Smoothing Probabilistic Laws)[RERUN] Episode Summary: In this podcast episode, we discuss the design of statistical learning machines which can make inferences about rare and unseen events using prior knowledge. Show Notes: Hello everyone! Welcome to a RERUN of the 11th podcast in the podcast series Learning Machines 101. In this… Read More »

LM101-026: How to Learn Statistical Regularities (Rerun)

Cartoon describing statistical learning with priors.

Podcast: Play in new window | Download | Embed

How to Learn Statistical Regularities using MAP and ML Estimation Episode Summary: 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. Show Notes: Hello everyone! Welcome to the tenth podcast in the… Read More »

LM101-025: How to Build a Lunar Lander Autopilot Learning Machine (adaptive control)

An illustration of a robot landing a lunar lander on the moon.

Podcast: Play in new window | Download | Embed

LM101-025: How to Build a Lunar Lander Autopilot Learning Machine (adaptive control) Episode Summary: 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… Read More »

LM101-024: How to Use Genetic Algorithms to Breed Learning Machines (Stochastic Model Search and Selection)

Monte Carlo Markov Chain Genetic Algorithms for Model Selection

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we explore the concept of evolutionary learning machines. That is, learning machines that reproduce themselves in the hopes of evolving into more intelligent and smarter learning machines. Show Notes: Hello everyone! Welcome to the twenty-fourth podcast in the podcast series Learning Machines 101. In this series of podcasts my goal is to discuss… Read More »

LM101-023: How to Build a Deep Learning Machine (Function Approximation)

Robot learning to play checkers using deep learning.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we discuss how to design and build “Deep Learning Machines” which can autonomously discover useful ways to represent knowledge of the world. Show Notes: Hello everyone! Welcome to the twenty-third podcast in the podcast series Learning Machines 101. In this series of podcasts my goal is to discuss important concepts of artificial intelligence… Read More »

LM101-022: How to Learn to Solve Large Constraint Satisfaction Problems (Expectation Maximization)

Contrastive Divergence Learning in pattern recognition machines as a neurally plausible theory of why people dream.

Podcast: Play in new window | Download | Embed

Episode Summary: 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. Show Notes: Hello everyone! Welcome to the twenty-second podcast in the podcast series Learning Machines 101. In this… Read More »

LM101-021: How to Solve Large Complex Constraint Satisfaction Problems (Monte Carlo Markov Chain)

Robot trying to solve a probabilistic constraint satisfaction problem.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode 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. Show Notes: Hello everyone! Welcome… Read More »

LM101-020: How to Use Nonlinear Machine Learning Software to Make Predictions

Gaussian mixture model and multilayer radial basis function machine learning software.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we describe how to download and use free nonlinear machine learning software which is more advanced than the linear machine software introduced in Episode 13. Show Notes: Hello everyone! Welcome to the twentieth podcast in the podcast series Learning Machines 101. In this series of podcasts my goal is to discuss important concepts… Read More »

LM101-019 (Rerun): How to Enhance Intelligence with a Robotic Body (Embodied Cognition)

Robot with human head playing racquetball and human with robot body.

Podcast: Play in new window | Download | Embed

Episode Summary: 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. Show Notes: Hello everyone! Welcome to the ninth podcast in the podcast series Learning Machines 101. In this series of podcasts my… Read More »

LM101-018 (Rerun): Can computers think? A mathematician’s response (Super Turing Computation)

Turing Machines versus Hypercomputation

Podcast: Play in new window | Download | Embed

Episode Summary: 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. (NOTE: This is a rerun of Episode… Read More »

LM101-017 (rerun): How to Decide if a Machine is Artificially Intelligent (The Turing Test)

Robot and human participating in the Turing Test.

Podcast: Play in new window | Download | Embed

Episode Summary: In this rerun of  episode 5 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. Show… Read More »

LM101-016: How to Analyze and Design Learning Rules using Gradient Descent Methods

Android robot skis downhill.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we introduce the concept of gradient descent which is the fundamental principle underlying learning in the majority of machine learning algorithms. Show Notes: Hello everyone! Welcome to the sixteenth podcast in the podcast series Learning Machines 101. In this series of podcasts my goal is to discuss important concepts of artificial intelligence and… Read More »

LM101-015: How to Build a Machine that Can Learn Anything (The Perceptron)

Multilayer feedforward neural network for binary classification.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we describe how to build a machine that can learn any given pattern of inputs and generate any desired pattern of outputs when it is possible to do so! Show Notes: Hello everyone! Welcome to the fifteenth podcast in the podcast series Learning Machines 101. In this series of podcasts my goal is… Read More »

LM101-014: How to Build a Machine that Can Do Anything (Function Approximation)

Robot building stuff with blocks.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we describe how to build a machine that can take any given pattern of inputs and generate any desired pattern of outputs! Show Notes: Hello everyone! Welcome to the fourteenth podcast in the podcast series Learning Machines 101. In this series of podcasts my goal is to discuss important concepts of artificial intelligence… Read More »

LM101-013: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software)

Android classifying a flower in the Iris Dataset.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we describe how to download and use free linear machine learning software to make predictions for classifying flower species using a famous machine learning data set. Show Notes: Hello everyone! Welcome to the thirteenth podcast in the podcast series Learning Machines 101. In this series of podcasts my goal is to discuss important… Read More »

LM101-012: How to Evaluate the Ability to Generalize from Experience (Cross-Validation Methods)

There is no correct interpretation of the identity of an ambiguous letter.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we discuss the problem of how to evaluate the ability of a learning machine to make generalizations and construct abstractions given the learning machine is provided a finite limited collection of experiences. Show Notes: Hello everyone! Welcome to the twelfth podcast in the podcast series Learning Machines 101. In this series of podcasts… Read More »

LM101-011: How to Learn About Rare and Unseen Events (Smoothing Probabilistic Laws)

How do you compute the probability of rare and unseen events?

Podcast: Play in new window | Download | Embed

Episode Summary: Today we address a strange yet fundamentally important question. How do you predict the probability of something you have never seen? Or, in other words, how can we accurately estimate the probability of rare events? Show Notes: Hello everyone! Welcome to the eleventh podcast in the podcast series Learning Machines 101. In this series of podcasts… Read More »

LM101-010: How to Learn Statistical Regularities (MAP and maximum likelihood estimation)

Cartoon describing statistical learning with priors.

Podcast: Play in new window | Download | Embed

Episode Summary: In this podcast episode, 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. Show Notes: Hello everyone! Welcome to the tenth podcast in the podcast series Learning Machines 101. In this series of podcasts my goal… Read More »

LM101-009: How to Enhance Intelligence with a Robotic Body (Embodied Cognition)

Robot with human head playing racquetball and human with robot body.

Podcast: Play in new window | Download | Embed

Episode Summary: 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. Show Notes: Hello everyone! Welcome to the ninth podcast in the podcast series Learning Machines 101. In this series of podcasts my… Read More »

LM101-008: How to Represent Beliefs using Probability Theory

Robot is using probabilistic inference to make deductions about world.

Podcast: Play in new window | Download | Embed

Episode Summary: This episode focusses upon how an intelligent system can represent beliefs about its environment using fuzzy measure theory. Probability theory is introduced as a special case of fuzzy measure theory which is consistent with classical laws of logical inference. Show Notes: Hello everyone! Welcome to the eighth podcast in the podcast series Learning Machines 101. In… Read More »

LM101-007: How to Reason About Uncertain Events using Fuzzy Set Theory and Fuzzy Measure Theory

Example of Logical Reasoning in an Environment Characterized by Uncertainty.

Podcast: Play in new window | Download | Embed

Episode Summary: In real life, there is no certainty. There are always exceptions. In this episode, two methods are discussed for making inferences in uncertain environments. In fuzzy set theory, a smart machine has certain beliefs about imprecisely defined concepts. In fuzzy measure theory, a smart machine has beliefs about precisely defined concepts but some beliefs are stronger… Read More »

LM101-006: How to Interpret Turing Test Results

Searle's Chinese Room argument against the validity of the Turing Test.

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode, we briefly review the concept of the Turing Test for Artificial Intelligence (AI) which states that if a computer’s behavior is indistinguishable from that of the behavior of a thinking human being, then the computer should be called “artificially intelligent”. Some objections to this definition of artificial intelligence are introduced and discussed. At… Read More »

LM101-005: How to Decide if a Machine is Artificially Intelligent (The Turing Test)

Robot and human participating in the Turing Test.

Podcast: Play in new window | Download | Embed

Episode Summary: 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. Show Notes: Hello everyone!… Read More »

LM101-004: Can computers think? A mathematician’s response

Turing Machines versus Hypercomputation

Podcast: Play in new window | Download | Embed

Episode Summary: 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. Show Notes: Hello everyone! Welcome to the… Read More »

LM101-003: How to Represent Knowledge using Logical Rules

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode we will learn how to use “rules” to represent knowledge. We discuss how this works in practice and we explain how these ideas are implemented in a special architecture called the production system. The challenges of representing knowledge using rules are also discussed. Specifically, these challenges include: issues of feature representation, having an… Read More »

LM101-002: How to Build a Machine that Learns to Play Checkers

Would anyone like to play a game of checkers?

Podcast: Play in new window | Download | Embed

Episode Summary: In this episode, we explain how to build a machine that learns to play checkers.  The solution to this problem involves several key ideas which are fundamental to building systems which are artificially intelligent. Show Notes: Hello everyone! Welcome to the second podcast in the podcast series Learning Machines 101. In this series of podcasts my… Read More »

LM101-001: Welcome to the Big Artificial Intelligence Magic Show!

Artificial Intelligence is like a magic show.

Podcast: Play in new window | Download | Embed

LM101-001: Welcome to the Big Artificial Intelligence Magic Show! Episode Summary: This episode discusses the similarities between designing an android that can command a starship and designing an android that can play a game of checkers. In addition, the mystery underlying both artificial intelligence and biological intelligence is discussed. Show Notes: Artificial Intelligence (AI) is a field of… Read More »