Flirting with Models cover image

John Alberg - The Man in the Machine (Learning) (S1E7)

Flirting with Models

00:00

Developing Confidence in Model Explainability and Adversarial Examples

The idea of adversarial examples is that a neural network can be trained to classify an image as an object. By changing one little tiny detail about the image, often imperceptible to the human eye, the neural network is completely confident it is not what the image is. But this balace of opaqueness and fragility of a neural network would almost require a higher degree of confidence to use it.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app