Learning Machines 101

By Richard M. Golden, Ph.D., M.S.E.E., B.S.E.E.

Technology Natural Sciences Science & Medicine Software How-To

What's Learning Machines 101 about?

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!

Download our free app to listen on your phone

LAST EPISODE

LM101-077: How to Choose th...

05.02.2019

In this 77th episode of www.learningmachines101.com , 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 ...

Learning Machines 101 episodes:

05.02.2019 LM101-077: How to Choose the Best Model using BIC In this 77th episode of www.learningmachines101.com , 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 ...
01.23.2019 LM101-076: How to Choose the Best Model using AIC and GAIC The precise semantic interpretation of the Akaike Information Criterion (AIC) and Generalized Akaike Information Criterion (GAIC) for selecting the best model are provided, explicit assumptions are provided for the AIC and GAIC to be valid, and explicit formulas are provided ...
12.12.2018 LM101-075: Can computers think? A Mathematician's Response (remix) 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 ...
06.30.2018 LM101-074: How to Represent Knowledge using Logical Rules (remix) The challenges of representing knowledge using rules are discussed. Specifically, these challenges include: issues of feature representation, having an adequate number of rules, obtaining rules that are not inconsistent, and having rules that handle special cases and situations. To learn ...
04.25.2018 LM101-073: How to Build a Machine that Learns to Play Checkers (remix) 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 checkers by itself without human intervention using a ...
03.31.2018 LM101-072: Welcome to the Big Artificial Intelligence Magic Show! (Remix of LM101-001 and LM101-002) 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 book "Computation as Done by Brains and ...
02.23.2018 LM101-071: How to Model Common Sense Knowledge using First-Order Logic and Markov Logic Nets This episode of Learning Machines 101 explains how to use first-order logic and Markov logic nets to represent common sense knowledge in machine learning algorithms links to free software for implementing Markov logic nets and a free database of common-sense ...
01.31.2018 LM101-070: How to Identify Facial Emotion Expressions in Images Using Stochastic Neighborhood Embedding 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 for: improving online communications, identifying terrorists, improving lie detector tests, improving athletic performance, and ...
12.16.2017 LM101-069: What Happened at the 2017 Neural Information Processing Systems Conference? 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 teaching learning machines rather than simply training them on examples. In addition, ...
09.26.2017 LM101-068: How to Design Automatic Learning Rate Selection for Gradient Descent Type Machine Learning Algorithms Simple mathematical formulas are presented that ensure convergence of a generated sequence of parameter vectors which are updated using an iterative algorithm consisting of adding a stepsize number multiplied by a search direction vector to the current parameter values and ...
08.21.2017 LM101-067: How to use Expectation Maximization to Learn Constraint Satisfaction Solutions (Rerun) 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 ...
07.17.2017 LM101-066: How to Solve Constraint Satisfaction Problems using MCMC Methods (Rerun) In this episode of Learning Machines 101 (www.learningmachines101.com) 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 ...
06.19.2017 LM101-065: How to Design Gradient Descent Learning Machines (Rerun) 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. Check out the website: www.learningmachines101.com to obtain a transcript of this ...
05.15.2017 LM101-064: Stochastic Model Search and Selection with Genetic Algorithms (Rerun) 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 smarter learning machines. This leads us to the topic of ...
04.20.2017 LM101-063: How to Transform a Supervised Learning Machine into a Policy Gradient Reinforcement Learning Machine 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 ...
03.19.2017 LM101-062: How to Transform a Supervised Learning Machine into a Value Function Reinforcement Learning Machine This 62nd episode of Learning Machines 101 (www.learningmachines101.com) 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 ...
02.23.2017 LM101-061: What happened at the Reinforcement Learning Tutorial? (RERUN) 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 ...
01.23.2017 LM101-060: How to Monitor Machine Learning Algorithms using Anomaly Detection Machine Learning Algorithms 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 ...
12.21.2016 LM101-059: How to Properly Introduce a Neural Network 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 of the neural network concept from its biological origins. For more ...
11.23.2016 LM101-058: How to Identify Hallucinating Learning Machines using Specification Analysis 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 the journal Econometrics in the special issue on model misspecification titled “Generalized Information Matrix Tests ...
10.18.2016 LM101-057: How to Catch Spammers using Spectral Clustering 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: www.learningmachines101.com
09.20.2016 LM101-056: How to Build Generative Latent Probabilistic Topic Models for Search Engine and Recommender System Applications 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 important and discuss how such algorithms can be used in the design of document ...
08.16.2016 LM101-055: How to Learn Statistical Regularities using MAP and Maximum Likelihood Estimation (Rerun) 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. In particular, the episode introduces ...
07.25.2016 LM101-054: How to Build Search Engine and Recommender Systems using Latent Semantic Analysis (RERUN) 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). The principles in this episode are also applicable to the ...
07.11.2016 LM101-053: How to Enhance Learning Machines with Swarm Intelligence (Particle Swarm Optimization) 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” is that you have a group of individual entities which behave ...
06.13.2016 LM101-052: How to Use the Kernel Trick to Make Hidden Units Disappear 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 you specify similarity relationships among input ...
05.24.2016 LM101-051: How to Use Radial Basis Function Perceptron Software for Supervised Learning[Rerun] 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 whose hidden units are radial basis functions. This ...
05.04.2016 LM101-050: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software)[RERUN] In this episode we will explain how to download and use free machine learning software from the website: www.learningmachines101.com. This podcast is concerned with the very practical issues associated with downloading and installing machine learning software on your computer. If ...
04.22.2016 LM101-049: How to Experiment with Lunar Lander Software 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 ...
03.29.2016 LM101-048: How to Build a Lunar Lander Autopilot Learning Machine (Rerun) 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 ...
03.14.2016 LM101-047: How Build a Support Vector Machine to Classify Patterns (Rerun) 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” which are important for characterizing the Support ...
02.23.2016 LM101-046: How to Optimize Student Learning using Recurrent Neural Networks (Educational Technology) 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 ...
02.08.2016 LM101-045: How to Build a Deep Learning Machine for Answering Questions about Images 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 describes a system which can answer simple questions about images. ...
01.26.2016 LM101-044: What happened at the Deep Reinforcement Learning Tutorial at the 2015 Neural Information Processing Systems Conference? 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 ...
01.12.2016 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 weekwill digress with a rerun of Episode 22 which nicely complements ...
12.29.2015 LM101-042: What happened at the Monte Carlo Markov Chain (MCMC) Inference Methods Tutorial at the 2015 Neural Information Processing Systems Conference? 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 field of ...
12.16.2015 LM101-041: What happened at the 2015 Neural Information Processing Systems Deep Learning Tutorial? 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. This is one of the top conferences in the field ...
11.24.2015 LM101-040: How to Build a Search Engine, Automatically Grade Essays, and Identify Synonyms using Latent Semantic Analysis 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 document, a paragraph of text, an essay, a sentence, or even just a single ...
11.09.2015 LM101-039: How to Solve Large Complex Constraint Satisfaction Problems (Monte Carlo Markov Chain and Markov Fields)[Rerun] 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 ...
10.27.2015 LM101-038: How to Model Knowledge Skill Growth Over Time using Bayesian Nets 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 knowledge state of a student a skill profile, and automatically defining the concept ...
10.12.2015 LM101-037: How to Build a Smart Computerized Adaptive Testing Machine using Item Response Theory 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 ...
09.28.2015 LM101-036: How to Predict the Future from the Distant Past using Recurrent Neural Networks 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. ...
09.15.2015 LM101-035: What is a Neural Network and What is a Hot Dog? 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. Check out: ...
08.25.2015 LM101-034: How to Use Nonlinear Machine Learning Software to Make Predictions (Feedforward Perceptrons with Radial Basis Functions)[Rerun] Welcome to the 34th podcast in the podcast series Learning Machines 101 titled "How to Use Nonlinear Machine Learning Software to Make Predictions". This particular podcast is a RERUN of Episode 20 and describes step by step how to download ...
08.10.2015 LM101-033: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software)[RERUN] In this episode will explain how to download and use free machine learning software which can be downloaded from the website: www.learningmachines101.com. The software can be used to make predictions using your own data sets. Although we will continue to ...
07.13.2015 LM101-032: How To Build a Support Vector Machine to Classify Patterns 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 ...
06.21.2015 LM101-031: How to Analyze and Design Learning Rules using Gradient Descent Methods (RERUN) 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 algorithms. Check out the transcripts of this episode and related references ...
06.08.2015 LM101-030: How to Improve Deep Learning Performance with Artificial Brain Damage (Dropout and Model Averaging) 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 units, and a relatively new learning strategy called "dropout" in which ...
05.25.2015 LM101-029: How to Modernize Deep Learning with Rectilinear units, Convolutional Nets, and Max-Pooling This podcast discusses talks, papers, and ideas presented at the recent International Conference on Learning Representations 2015 which was followed by the Artificial Intelligence in Statistics 2015 Conference in San Diego. Specifically, commonly used techniques shared by many successful deep ...
05.11.2015 LM101-028: How to Evaluate the Ability to Generalize from Experience (Cross-Validation Methods)[RERUN] This rerun of an earlier episode of Learning Machines 101 discusses 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 ...

Older episodes