Podcasts by Learning Machines 101
Smart machines based upon the principles of artificial intelligence and machine learning are now prevalent in our everyday life. For example, artificially intelligent systems recognize our voices, sort our pictures, make purchasing suggestions, and can automatically fly planes and drive cars. In this podcast series, we examine such questions such as: How do these devices work? Where do they come from? And how can we make them even smarter and more human-like? These are the questions that will be addressed in this podcast series!
Further podcasts by Richard M. Golden, Ph.D., M.S.E.E., B.S.E.E.
Podcast on the topic Technologie
All episodes
LM101-086: Ch8: How to Learn the Probability of Infinitely Many Outcomes from 2021-07-20T23:23:53
This 86th episode of Learning Machines 101 discusses the problem of assigning probabilities to a possibly infinite set of outcomes in a space-time continuum which characterizes our physical worl...
ListenLM101-085:Ch7:How to Guarantee your Batch Learning Algorithm Converges from 2021-05-21T00:59:35
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 usi...
ListenLM101-084: Ch6: How to Analyze the Behavior of Smart Dynamical Systems from 2021-01-05T20:10:58
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 ma...
ListenLM101-083: Ch5: How to Use Calculus to Design Learning Machines from 2020-08-29T13:21:11
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 i...
ListenLM101-082: Ch4: How to Analyze and Design Linear Machines from 2020-07-23T22:57:37
The main focus of this particular episode covers the material in Chapter 4 of my new forthcoming book titled “Statistical Machine Learn...
ListenLM101-081: Ch3: How to Define Machine Learning (or at Least Try) from 2020-04-09T14:30:14
This particular podcast covers the material in Chapter 3 of my new book “Statistical Machine Learning: A unified framework” with expected pu...
ListenLM101-080: Ch2: How to Represent Knowledge using Set Theory from 2020-02-29T22:56:56
This particular podcast covers the material in Chapter 2 of my new book “Statistical Machine Learning: A unified framework” with expected pu...
ListenLM101-079: Ch1: How to View Learning as Risk Minimization from 2019-12-24T00:06:36
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, wh...
ListenLM101-078: Ch0: How to Become a Machine Learning Expert from 2019-10-24T01:07:35
This particular podcast (Episode 78 of Learning Machines 101) is the initial episode in a new special series of episodes designed to provide commentary on a new book that I am in the process of ...
ListenLM101-077: How to Choose the Best Model using BIC from 2019-05-02T03:03:38
In this 77th episode of www.learningmachines101.com , we explain the proper semantic interpretation of the Bayesian Information Criterion (BIC)...
ListenLM101-076: How to Choose the Best Model using AIC and GAIC from 2019-01-23T04:27:32
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 be...
ListenLM101-075: Can computers think? A Mathematician's Response (remix) from 2018-12-12T06:27:23
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 compu...
ListenLM101-074: How to Represent Knowledge using Logical Rules (remix) from 2018-06-30T02:35:51
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...
ListenLM101-073: How to Build a Machine that Learns to Play Checkers (remix) from 2018-04-25T23:42:42
This is a remix of the original second episode Learning Machines 101 which describes in a little more detail how the computer program that Arthur Samuel developed in 1959 learned to play checker...
ListenLM101-072: Welcome to the Big Artificial Intelligence Magic Show! (Remix of LM101-001 and LM101-002) from 2018-03-31T02:23:34
This podcast is basically a remix of the first and second episodes of Learning Machines 101 and is intended to serve as the new introduction to the Learning Machines 101 podcast series. The sear...
ListenLM101-071: How to Model Common Sense Knowledge using First-Order Logic and Markov Logic Nets from 2018-02-23T23:02:38
In this podcast, we provide some insights into the complexity of common sense. First, we discuss the importance of building common sense into learning machines. Second, we discuss how first-orde...
ListenLM101-070: How to Identify Facial Emotion Expressions in Images Using Stochastic Neighborhood Embedding from 2018-01-31T23:00:36
This 70th episode of Learning Machines 101 we discuss how to identify facial emotion expressions in images using an advanced clustering technique called Stochastic Neighborhood Embedding. We dis...
ListenLM101-069: What Happened at the 2017 Neural Information Processing Systems Conference? from 2017-12-16T16:51:45
This 69th episode of Learning Machines 101 provides a short overview of the 2017 Neural Information Processing Systems conference with a focus on the development of methods for teachi...
ListenLM101-068: How to Design Automatic Learning Rate Selection for Gradient Descent Type Machine Learning Algorithms from 2017-09-26T01:52:37
This 68th episode of Learning Machines 101 discusses a broad class of unsupervised, supervised, and reinforcement machine learning algorithms which iteratively update their parameter vector by a...
ListenLM101-067: How to use Expectation Maximization to Learn Constraint Satisfaction Solutions (Rerun) from 2017-08-21T11:00
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 unobserva...
ListenLM101-066: How to Solve Constraint Satisfaction Problems using MCMC Methods (Rerun) from 2017-07-17T17:00
In this episode of Learning Machines 101 (www.learningmachines101.com) we discuss how to solve constraint satisfaction inference problems where ...
ListenLM101-065: How to Design Gradient Descent Learning Machines (Rerun) from 2017-06-19T15:00
In this episode rerun 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....
ListenLM101-064: Stochastic Model Search and Selection with Genetic Algorithms (Rerun) from 2017-05-15T17:00
In this rerun of episode 24 we explore the concept of evolutionary learning machines. That is, learning machines that reproduce themselves in the hopes of evolving into more intelligent and smar...
ListenLM101-063: How to Transform a Supervised Learning Machine into a Policy Gradient Reinforcement Learning Machine from 2017-04-20T04:16:31
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 acti...
ListenLM101-062: How to Transform a Supervised Learning Machine into a Value Function Reinforcement Learning Machine from 2017-03-19T01:52:23
This 62nd episode of Learning Machines 101 (www.learningmachines101.com) discusses how to design reinforcement learning machines using your kno...
ListenLM101-061: What happened at the Reinforcement Learning Tutorial? (RERUN) from 2017-02-23T02:07:06
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...
ListenLM101-060: How to Monitor Machine Learning Algorithms using Anomaly Detection Machine Learning Algorithms from 2017-01-23T04:14:11
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 algor...
ListenLM101-059: How to Properly Introduce a Neural Network from 2016-12-21T05:16:22
I discuss the concept of a “neural network” by providing some examples of recent successes in neural network machine learning algorithms and providing a historical perspective on the evolution o...
ListenLM101-058: How to Identify Hallucinating Learning Machines using Specification Analysis from 2016-11-23T03:49:19
In this 58th episode of Learning Machines 101, I’ll be discussing an important new scientific breakthrough published just last week for the first time in Listen
LM101-057: How to Catch Spammers using Spectral Clustering from 2016-10-18T03:44:05
In this 57th episode, we explain how to use unsupervised machine learning algorithms to catch internet criminals who try to steal your money electronically! Check it out at: Listen
LM101-056: How to Build Generative Latent Probabilistic Topic Models for Search Engine and Recommender System Applications from 2016-09-20T01:22:23
In this NEW episode we discuss Latent Semantic Indexing type machine learning algorithms which have a PROBABILISTIC interpretation. We explain why such a probabilistic interpretation is importa...
ListenLM101-055: How to Learn Statistical Regularities using MAP and Maximum Likelihood Estimation (Rerun) from 2016-08-16T03:54:54
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 gu...
ListenLM101-054: How to Build Search Engine and Recommender Systems using Latent Semantic Analysis (RERUN) from 2016-07-25T19:41:32
Welcome to the 54th Episode of Learning Machines 101 titled "How to Build a Search Engine, Automatically Grade Essays, and Identify Synonyms using Latent Semantic Analysis" (rerun of Episode 40)...
ListenLM101-053: How to Enhance Learning Machines with Swarm Intelligence (Particle Swarm Optimization) from 2016-07-11T18:31:29
In this 53rd episode of Learning Machines 101, we introduce the concept of a Swarm Intelligence with respect to Particle Swarm Optimization Algorithms. The essential idea of “Swarm Intelligence”...
ListenLM101-052: How to Use the Kernel Trick to Make Hidden Units Disappear from 2016-06-13T10:00
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 of the “Kernel Trick” is that ...
ListenLM101-051: How to Use Radial Basis Function Perceptron Software for Supervised Learning[Rerun] from 2016-05-24T16:37:58
This particular podcast is a RERUN of Episode 20 and describes step by step how to download free software which can be used to make predictions using a feedforward artificial neural network whos...
ListenLM101-050: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software)[RERUN] from 2016-05-04T01:53:26
In this episode we will explain how to download and use free machine learning software from the website: www.learningmachines101.com. This podca...
ListenLM101-049: How to Experiment with Lunar Lander Software from 2016-04-22T15:53:09
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 t...
ListenLM101-048: How to Build a Lunar Lander Autopilot Learning Machine (Rerun) from 2016-03-29T01:40:10
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 so...
ListenLM101-047: How Build a Support Vector Machine to Classify Patterns (Rerun) from 2016-03-14T23:53:24
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 pattern vectors called “support vectors” ...
ListenLM101-046: How to Optimize Student Learning using Recurrent Neural Networks (Educational Technology) from 2016-02-23T04:55:07
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 fi...
ListenLM101-045: How to Build a Deep Learning Machine for Answering Questions about Images from 2016-02-08T22:44:53
In this episode we discuss just one out of the 102 different posters which was presented on the first night of the 2015 Neural Information Processing Systems Conference. This presentation descri...
ListenLM101-044: What happened at the Deep Reinforcement Learning Tutorial at the 2015 Neural Information Processing Systems Conference? from 2016-01-26T05:11:09
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...
ListenLM101-043: How to Learn a Monte Carlo Markov Chain to Solve Constraint Satisfaction Problems (Rerun of Episode 22) from 2016-01-12T03:50:24
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 Conferenc...
LM101-042: What happened at the Monte Carlo Markov Chain (MCMC) Inference Methods Tutorial at the 2015 Neural Information Processing Systems Conference? from 2015-12-29T03:10:53
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 i...
ListenLM101-041: What happened at the 2015 Neural Information Processing Systems Deep Learning Tutorial? from 2015-12-16T04:44:21
This is the first 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. Th...
ListenLM101-040: How to Build a Search Engine, Automatically Grade Essays, and Identify Synonyms using Latent Semantic Analysis from 2015-11-24T06:14:16
In this episode we introduce a very powerful approach for computing semantic similarity between documents. Here, the terminology “document” could refer to a web-page, a word do...
ListenLM101-039: How to Solve Large Complex Constraint Satisfaction Problems (Monte Carlo Markov Chain and Markov Fields)[Rerun] from 2015-11-09T22:44:26
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...
ListenLM101-038: How to Model Knowledge Skill Growth Over Time using Bayesian Nets from 2015-10-27T02:35:33
In this episode, we examine the problem of developing an advanced artificially intelligent technology which is capable of tracking knowledge growth in students in real-time, representing the kno...
ListenLM101-037: How to Build a Smart Computerized Adaptive Testing Machine using Item Response Theory from 2015-10-12T14:00
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 targe...
ListenLM101-036: How to Predict the Future from the Distant Past using Recurrent Neural Networks from 2015-09-28T22:03:49
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 whi...
ListenLM101-035: What is a Neural Network and What is a Hot Dog? from 2015-09-15T05:45:41
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 Atar...
ListenLM101-034: How to Use Nonlinear Machine Learning Software to Make Predictions (Feedforward Perceptrons with Radial Basis Functions)[Rerun] from 2015-08-25T00:08:32
Welcome to the 34t...
ListenLM101-032: How To Build a Support Vector Machine to Classify Patterns from 2015-07-13T18:00
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 cl...
ListenLM101-031: How to Analyze and Design Learning Rules using Gradient Descent Methods (RERUN) from 2015-06-21T17:00
In this rerun of Episode 16, we introduce the important concept of gradient descent which is the fundamental principle underlying learning mechanisms in a wide range of machine learning algorith...
ListenLM101-030: How to Improve Deep Learning Performance with Artificial Brain Damage (Dropout and Model Averaging) from 2015-06-08T22:53:28
Deep learning machine technology has rapidly developed over the past five years due in part to a variety of actors such as: better technology, convolutional net algorithms, rectified linear unit...
ListenLM101-029: How to Modernize Deep Learning with Rectilinear units, Convolutional Nets, and Max-Pooling from 2015-05-25T19:57:52
This podcast discusses talks, papers, and ideas presented at the recent International Conference on Learning Representations 2015 whic...
ListenLM101-028: How to Evaluate the Ability to Generalize from Experience (Cross-Validation Methods)[RERUN] from 2015-05-11T12:00
This rerun of an earlier episode of Learning Machine...
ListenLM101-027: How to Learn About Rare and Unseen Events (Smoothing Probabilistic Laws)[RERUN] from 2015-04-28T03:10:01
In this episode of Learning Machines 101 we discuss the design of sta...
ListenLM101-026: How to Learn Statistical Regularities (Rerun) from 2015-04-14T00:22:23
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...
ListenLM101-025: How to Build a Lunar Lander Autopilot Learning Machine from 2015-03-24T01:35:32
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...
ListenLM101-024: How to Use Genetic Algorithms to Breed Learning Machines from 2015-03-10T03:40:58
...
ListenLM101-022: How to Learn to Solve Large Constraint Satisfaction Problems from 2015-02-10T00:36:07
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 va...
ListenLM101-021: How to Solve Large Complex Constraint Satisfaction Problems (Monte Carlo Markov Chain) from 2015-01-26T20:12:25
We discuss how to solve constraint satisfaction inference problems where knowledge is represented as a large unordered collection of complicated probabilistic constraints among...
ListenLM101-020: How to Use Nonlinear Machine Learning Software to Make Predictions from 2015-01-12T23:26:58
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 imp...
ListenLM101-019 (Rerun): How to Enhance Intelligence with a Robotic Body (Embodied Cognition) from 2014-12-22T07:00
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 artifici...
ListenLM101-018: Can Computers Think? A Mathematician's Response (Rerun) from 2014-12-12T08:00
In this episode, we explore the question of what can computers do as well as what computers can...
ListenLM101-017: How to Decide if a Machine is Artificially Intelligent (Rerun) from 2014-11-24T18:00
This episode we discuss the Turing Test for Artificial Intelligence which is designed to determ...
ListenLM101-016: How to Analyze and Design Learning Rules using Gradient Descent Methods from 2014-11-11T01:57:20
In this episode we introduce the concept of gradient descent which is the fundamental principle underlying learning in the majority of machine learning algorithms.
LM101-015: How to Build a Machine that Can Learn Anything (The Perceptron) from 2014-10-27T12:39:18
In this 15th episode of Learning Machines 101, we discuss the problem of how to build a machine that can learn any given pattern of inputs and generate any desired pattern of o...
ListenLM101-014: How to Build a Machine that Can Do Anything (Function Approximation) from 2014-10-13T23:08:04
In this episode, we discuss the problem of how to build a machine that can do anything! Or more specifically, given a set of input patterns to the machine and a set of desired ...
ListenLM101-013: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software) from 2014-09-22T22:46:14
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 concepts of a...
ListenLM101-012: How to Evaluate the Ability to Generalize from Experience (Cross-Validation Methods) from 2014-09-09T00:20:14
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 pro...
ListenLM101-008: How to Represent Beliefs Using Probability Theory from 2014-09-03T20:27:14
Episode Summary: This episode focusses upon how an intelligent system can rep...
ListenLM101-011: How to Learn About Rare and Unseen Events (Smoothing Probabilistic Laws) from 2014-08-26T01:44:06
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: Today we add...
ListenLM101-010: How to Learn Statistical Regularities (MAP and maximum likelihood estimation) from 2014-08-12T00:52:50
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: In this podc...
ListenLM101-009: How to Enhance Intelligence with a Robotic Body (Embodied Cognition) from 2014-07-28T12:00:22
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: Embodied cog...
ListenLM101-007: How to Reason About Uncertain Events using Fuzzy Set Theory and Fuzzy Measure Theory from 2014-06-23T23:33:58
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: In real life...
ListenLM101-006: How to Interpret Turing Test Results from 2014-06-09T12:00:04
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: In this epis...
ListenLM101-005: How to Decide if a Machine is Artificially Intelligent (The Turing Test) from 2014-05-27T02:10:20
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: This episode...
ListenLM101-004: Can computers think? A mathematician.s response from 2014-05-12T12:00:57
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: In this epis...
ListenLM101-003: How to Represent Knowledge using Logical Rules from 2014-04-29T06:48:08
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: In this epis...
ListenLM101-002: How to Build a Machine that Learns to Play Checkers from 2014-04-29T06:36:17
Learning Machines 101 - A Gentle Introduction to Artificial Intelligence and Machine Learning
Episode Summary: In this epis...
Listen