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

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 »

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

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 »

LM101-062: How to Transform a Supervised Learning Machine into a Value Function Reinforcement Learning Machine

LM101-062: How to Transform a Supervised Learning Machine into a Value Function Reinforcement Learning Machine Episode Summary: This 62nd episode of Learning Machines 101 discusses how to design reinforcement learning machines using your knowledge of how to build supervised learning machines! Specifically, we focus on Value Function Reinforcement Learning Machines which estimate the unobservable total penalty associated with… Read More »

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

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 »

LM101-076: How To Choose the Best Model using AIC or GAIC

Episode Summary: In this episode, we explain the proper semantic interpretation of the Akaike Information Criterion (AIC) and the Generalized Akaike Information Criterion (GAIC) for the purpose of picking the best model for a given set of training data.  The precise semantic interpretation of these model selection criteria is provided, explicit assumptions are provided for the AIC and… Read More »

LM101-063: How to Transform a Supervised Learning Machine into a Policy Gradient Reinforcement Learning Machine

LM101-063: How to Transform a Supervised Learning Machine into a Policy Gradient Reinforcement Learning Machine Episode Summary: This 63rd episode of Learning Machines 101 discusses how to build reinforcement learning machines which become smarter with experience but do not use this acquired knowledge to modify their actions and behaviors. This episode explains how to build reinforcement learning machines… Read More »

LM101-061: What happened at the Reinforcement Learning Tutorial? (RERUN)

LM101-061: What happened at the Reinforcement Learning Tutorial? (RERUN) Episode Summary: This is the third of a short subsequence of podcasts providing a summary of events associated with Dr. Golden’s recent visit to the 2015 Neural Information Processing Systems Conference. This is one of the top conferences in the field of Machine Learning. This episode reviews and discusses… Read More »

LM101-052: How to Use the Kernel Trick to Make Hidden Units Disappear

LM101-052: How to Use the Kernel Trick to Make Hidden Units Disappear Episode Summary: Today, we discuss a simple yet powerful idea which began popular in the machine learning literature in the 1990s which is called “The Kernel Trick”. The basic idea behind “The Kernel Trick” is that an impossible machine learning problem can be transformed into an… Read More »

LM101-046: How to Optimize Student Learning using Recurrent Neural Networks (Educational Technology)

LM101-046: How to Optimize Student Learning using Recurrent Neural Networks (Educational Technology) Episode Summary: In this episode, we briefly review Item Response Theory and Bayesian Network Theory methods for the assessment and optimization of student learning and then describe a poster presented on the first day of the Neural Information Processing Systems conference in December 2015 in Montreal… Read More »

LM101-044: What happened at the Deep Reinforcement Learning Tutorial at the 2015 Neural Information Processing Systems Conference?

LM101-044: What happened at the Deep Reinforcement Learning Tutorial at the 2015 Neural Information Processing Systems Conference? Episode Summary: This is the third of a short subsequence of podcasts providing a summary of events associated with Dr. Golden’s recent visit to the 2015 Neural Information Processing Systems Conference. This is one of the top conferences in the field… Read More »

LM101-037: How to Build a Smart Computerized Adaptive Testing Machine using Item Response Theory

LM101-037: How to Build a Smart Computerized Adaptive Testing Machine using Item Response Theory Episode Summary: In this episode, we discuss the problem of how to build a smart computerized adaptive testing machine using Item Response Theory (IRT). Suppose that you are teaching a student a particular target set of knowledge. Examples of such situations obviously occur in… Read More »

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

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 »

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

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 »

LM101-085: Ch7: How to Guarantee your Batch Learning Algorithm Converges

This 85th episode of Learning Machines 101 discusses formal convergence guarantees for a broad class of machine learning algorithms designed to minimize smooth non-convex objective functions using batch learning methods. In particular, a broad class of unsupervised, supervised, and reinforcement machine learning algorithms which iteratively update their parameter vector by adding a perturbation based upon all of the training data. This process is repeated, making a perturbation of the parameter vector based upon all of the training data until a parameter vector is generated which exhibits improved predictive performance. The magnitude of the perturbation at each learning iteration is called the “stepsize” or “learning rate” and the identity of the perturbation vector is called the “search direction”. Simple mathematical formulas are presented based upon research from the late 1960s by Philip Wolfe and G. Zoutendijk that ensure convergence of the generated sequence of parameter vectors. These formulas may be used as the basis for the design of artificially intelligent smart automatic learning rate selection algorithms. The material in this podcast is designed to provide an overview of Chapter 7 of my new book “Statistical Machine Learning” and is based upon material originally presented in Episode 68 of Learning Machines 101!

LM101-082: Ch4: How to Analyze and Design Linear Machines

Episode Summary: This particular podcast covers the material in Chapter 4 of my new book “Statistical Machine Learning: A unified framework” which is now available! Many important and widely used machine learning algorithms may be interpreted as linear machines and this chapter shows how to use linear algebra to analyze and design such machines. In addition, these same… Read More »

LM101-077: How to Choose the Best Model using BIC

Episode Summary: In this episode, we explain the proper semantic interpretation of the Bayesian Information Criterion (BIC) and emphasize how this semantic interpretation is fundamentally different from AIC (Akaike Information Criterion) model selection methods. Briefly, BIC is used to estimate the probability of the training data given the probability model, while AIC is used to estimate out-of-sample prediction… Read More »

LM101-075: Can computers think? A Mathematician’s Response using a Turing Machine Argument (remix)

LM101-075: Can computers think? A Mathematician’s Response using a Turing Machine Argument (remix) 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… Read More »

LM101-067: How to use Expectation Maximization to Learn Constraint Satisfaction Solutions (Rerun)

LM101-067: How to use Expectation Maximization to Learn Constraint Satisfaction Solutions (Rerun) 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. Specifically, the important machine learning method… Read More »

LM101-065: How to Design Gradient Descent Learning Machines (Rerun)

LM101-065: How to Design Gradient Descent Learning Machines (Rerun) Episode Summary: In this episode we introduce the concept of gradient descent which is the fundamental principle underlying learning in the majority of deep learning and neural network learning algorithms. Show Notes: Hello everyone! Welcome to the sixteenth podcast in the podcast series Learning Machines 101. In this series… Read More »

LM101-060: How to Monitor Machine Learning Algorithms using Anomaly Detection Machine Learning Algorithms

LM101-060: How to Monitor Machine Learning Algorithms using Anomaly Detection Machine Learning Algorithms Episode Summary: This 60th episode of Learning Machines 101 discusses how one can use novelty detection or anomaly detection machine learning algorithms to monitor the performance of other machine learning algorithms deployed in real world environments. The episode is based upon a review of a… Read More »

LM101-057: How to Catch Spammers using Spectral Clustering

LM101-057: How to Catch Spammers using Spectral Clustering Episode Summary: In this 57th episode, we explain how to use spectral cluster analysis unsupervised machine learning algorithms to catch internet criminals who try to steal your money electronically! Show Notes: Hello everyone! Welcome to the fifty-seventh podcast in the podcast series Learning Machines 101. In this series of podcasts… Read More »

LM101-049: How to Experiment with Lunar Lander Software

LM101-049: How to Experiment with Lunar Lander Software Episode Summary: In this episode we continue the discussion of learning when the actions of the learning machine can alter the characteristics of the learning machine’s statistical environment. We describe how to download free lunar lander software so you can experiment with an autopilot for a lunar lander module that… Read More »

LM101-047: How to Build a Support Vector Machine to Classify Patterns (Rerun)

  LM101-047: How To Build a Support Vector Machine to Classify Patterns (Rerun) Episode Summary: In this RERUN of the 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… Read More »

LM101-045: How to Build a Deep Learning Machine for Answering Questions about Images

LM101-045: How to Build a Deep Learning Machine for Answering Questions about Images Episode Summary: This is the fourth of a short subsequence of podcasts which provides a summary of events associated with Dr. Golden’s recent visit to the 2015 Neural Information Processing Systems Conference. This is one of the top conferences in the field of Machine Learning. This… Read More »

LM101-043: How to Learn a Monte Carlo Markov Chain to Solve Constraint Satisfaction Problems (Rerun)

LM101-043: How to Learn a Monte Carlo Markov Chain to Solve Constraint Satisfaction Problems (Rerun of Episode 22) Welcome to the 43rd Episode of Learning Machines 101! We are currently presenting a subsequence of episodes covering the events of the recent Neural Information Processing Systems Conference. However, this week will digress with a rerun of Episode 22 which… Read More »

LM101-042: What happened at the Monte Carlo Markov Chain Inference Methods Tutorial at the 2015 Neural Information Processing Systems Conference?

LM101-042: What happened at the Monte Carlo Inference Methods Tutorial at the 2015 Neural Information Processing Systems Conference? Episode Summary: This is the second of a short subsequence of podcasts providing a summary of events associated with Dr. Golden’s recent visit to the 2015 Neural Information Processing Systems Conference. This is one of the top conferences in the… Read More »

LM101-041: What happened at the 2015 Neural Information Processing Systems Deep Learning Tutorial?

LM101-041: What happened at the 2015 Neural Information Processing Systems Deep Learning Tutorial? Episode Summary: This is the first of a short subsequence of podcasts which provides a summary of events at the recent 2015 Neural Information Processing Systems Conference. This is one of the top conferences in the field of Machine Learning. This episode introduces the Neural… Read More »

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

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?

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 »

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

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)

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)

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 »

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

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 »

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

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 »

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

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 »

LM101-008: How to Represent Beliefs using Probability Theory

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 »

LM101-006: How to Interpret Turing Test Results

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 »

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

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 »