AI Today Podcast: Interview with Mignon Clyburn, Commissioner for the National Security Commission on AI (NSCAI)

In order for machine learning systems to work they need to be trained on data. But as the old saying goes “garbage in is garbage out” so you need to make sure you have a dataset of prepared data that ...

28 Apr 202311min

Backpropagation was one of the innovations by Geoff Hinton that made deep learning networks a practical reality. But have you ever heard of that term before and know what it is at a high level? In thi...

26 Apr 202311min

In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms Loss Function, Cost Function and Gradient Descent, explain how these terms relates to AI and why it’s im...

21 Apr 202312min

Deep Learning is powering this current wave of AI interest. But do you really know what Deep Learning is? In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the term...

19 Apr 202312min

The Perceptron was the first artificial neuron. The theory of the perceptron was first published in 1943 by McCulloch & Pitts, and then developed in 1958 by Rosenblatt. So yes, this was developed in t...

14 Apr 202312min

In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms Bias, Weight, Activation Function, Convergence, and ReLU and explain how they relate to AI and why it’s ...

12 Apr 202313min

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 (Ar...

7 Apr 202313min

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. Bu...

5 Apr 202310min