AI Today Podcast

If we can replicate neurons and how they are connected, can we replicate the behavior of our brains? In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms (Artificial) Neural Networks, Node, and layer, and explain how they relate to AI an...

For a number of reasons, it can be important to reduce the number of variables or identified features in input training data so as to make training machine learning models faster and more accurate. But what are the techniques for doing this? In this episode of the AI Today podcas...

For time-consuming parts of the machine learning workflow people often look for tricks and techniques to help speed up the process. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms feature and feature engineering, explain how they re...

Regression is a statistical and mathematical technique to find the relationship between two or more variables. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms Regression and Linear Regression and explain how they relate to AI and wh...

The idea of grouping similar types of data together is the main idea behind clustering. Clustering supports the goals of Unsupervised Learning which is finding patterns in data without requiring labeled datasets. In this episode of the AI Today podcast hosts Kathleen Walch and Ro...

In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define DeepBlue, including what it is and why it’s notable for AI.
Show Notes:
• FREE Intro to CPMAI mini course
• CPMAI Training and Certification
• AI Glossary
• AI Glossary Series – Symbolic Systems...

Before this latest wave of AI where neural nets became the hottest algorithm of choice, an approach to machine learning that uses logic and constructs similar to the way that humans reason through problems called Symbolic Systems were actually the system of choice. Popularized in...

Sometimes for reasons such as improving performance or robustness it makes sense to create multiple decision trees and average the results to solve problems related to overfitting. Or, it makes sense to boost certain decision trees. In this episode of the AI Today podcast hosts K...

Sometimes for reasons such as improving performance or robustness it makes sense to combine the results of multiple different models trained on the same data. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the term Ensemble Models, and expla...

There are many algorithms that can be used for classification and it’s important to at least know them at a high level. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms Support Vector Machine & Kernel Method, and explain how they rel...

There are many algorithms that can be used for classification and it’s important to at least know them at a high level. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms Support Vector Machine & Kernel Method, and explain how they rel...

There are many algorithms that can be used for classification and it’s important to at least know them at a high level. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms K-Nearest Neighbor and Lazy Learning, and explain how they relat...