Ep 116: Bit seat drivers



Bit seat drivers

Deep learning algorithms, and neural networks in general, require much more training than humans do. They are unable to generalize well enough to handle situations not covered in the training data, and can be thrown off by things that a human wouldn’t even notice. Today we look at these challenges by examining what it takes to train a neural network to drive a car.

Here are a couple of links about training self-driving vehicles.

Edge case training and discovery are keeping self-driving cars from gaining full autonomy

Training AI for Self-Driving Vehicles: the Challenge of Scale

Here’s a short video demo and an article about how AI image recognition can be fooled by things that wouldn’t fool many animals.

Adversarial Patch

Google ‘optical illusion’ stickers make AI hallucinate


Leave a Reply