logo
episode-header-image
Jul 2023
42m 1s

Machine Learning and Catastrophic Forget...

iHeartPodcasts
About this episode

While an elephant may never forget, the same cannot be said for artificial neural networks. What is catastrophic forgetting, how does it affect artificial intelligence and how are engineers trying to solve the problem? 

See omnystudio.com/listener for privacy information.

Up next
Today
The Story: What Does the Future of War Look Like?
<p>This week, what does defense technology look like in 2025? Oz talks to Pulitzer Prize-winning journalist Dexter Filkins about his recent piece in&nbsp;<em>The New Yorker</em> titled &ldquo;Is the US ready for the next war?&rdquo; They discuss how the Ukraine and Israel are rei ... Show More
32m 34s
Nov 21
Week in Tech: Could a Dead Cat Sink Waymo?
<p>Would you buy a boat or a midcentury sideboard from your high school pals? Because Oz&rsquo;s alma mater has opened an <em>exclusive</em> online marketplace for just this purpose! This week, Oz spins a yarn about Kitkat, the San Francisco cat killed by a Waymo. Locals are furi ... Show More
32m 47s
Nov 19
The Story: The UK’s Race for Second Place in the Chip Wars
<p>This week, Oz talks to Nick McKeown, who is a member of the PM&rsquo;s Council of Science and Technology, where he advises the British government on the best opportunities for economic growth in the tech sector. And according to Nick, that opportunity is AI Chips. He argues th ... Show More
30m 36s
Recommended Episodes
May 2024
Audio long read: How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models
AIs are often described as 'black boxes' with researchers unable to to figure out how they 'think'. To better understand these often inscrutable systems, some scientists are borrowing from psychology and neuroscience to design tools to reverse-engineer them, which they hope will ... Show More
17m 41s
Jul 2023
Tech and AI: 6. What is AI?
Artificial Intelligence has been in the news constantly this year, from a chatbot that can write anything you can imagine, in any style, to scientists and world leaders warning that AI needs to be controlled. With the big tech firms all rushing to make their AI products available ... Show More
13m 50s
Jan 2023
24. Artificial Intelligence: What Is It? What Is It Not? (feat. Susan Farrell, Principal UX Researcher at mmhmm.app)
<p>The term artificial intelligence, AI, is having a bit of a boom, with the explosion in popularity of tools like ChatGPT, Lensa, DALL•E 2, and many others. The praises of AI have been equally met with skepticism and criticism, with cautionary tales about AI information quality, ... Show More
35m 35s
Nov 2020
What Algorithms Say About You
Artificial intelligence is letting us make predictive algorithms that translate languages and spot diseases as well or better than humans. But these systems are also being used to make decisions about hiring and criminal sentencing. Do computers trained on vast datasets of human ... Show More
1h 10m
Jul 2023
Tech and AI: 10. Can we control AI?
When so-called "generative" Artificial Intelligences like Chat GPT and Google's Bard were made available to the public, they made headlines around the world and raised fears about how fast this type of AI was developing. But realistically, what harm could AI do to people? Is it a ... Show More
13m 51s
Feb 2023
What is Artificial Intelligence?
Lets learn about artificial intelligence and how it works! 
5m 5s
Feb 2016
Paradigms in Artificial Intelligence
Artificial intelligence includes a number of different strategies for how to make machines more intelligent, and often more human-like, in their ability to learn and solve problems. An ambitious group of researchers is working right now to classify all the approaches to AI, perha ... Show More
17m 20s
Sep 2023
Computers are learning to read our minds
<p><a href="https://vcresearch.berkeley.edu/faculty/gasper-begus" target="_blank">Gašper</a>’s work combines machine learning, statistical modeling, neuroimaging, and behavioral experiments “to better understand how neural networks learn internal representations in speech and how ... Show More
30m 6s
Jul 2022
Why Artificial Intelligence Projects Fail ?
Podcast with Gautam Siwach and Jin Vanstee ! Speaker - Elpida Tzortzatos is an IBM Fellow and CTO AI on IBM zSystems. In this Podcast we listen to Elpida's thoughts about driving Artificial Intelligence strategies, associated risks, and Values.We will learn how to drive industry- ... Show More
10m 50s