📚 node [[exploding_gradient_problem]]
📓
garden/KGBicheno/Artificial Intelligence/Introduction to AI/Week 3 - Introduction/Definitions/Exploding_Gradient_Problem.md by @KGBicheno
exploding gradient problem
Go back to the [[AI Glossary]]
#seq
The tendency for gradients in a deep neural networks (especially recurrent neural networks) to become surprisingly steep (high). Steep gradients result in very large updates to the weights of each node in a deep neural network.
Models suffering from the exploding gradient problem become difficult or impossible to train. Gradient clipping can mitigate this problem.
Compare to vanishing gradient problem.
F
📖 stoas
- public document at doc.anagora.org/exploding_gradient_problem
- video call at meet.jit.si/exploding_gradient_problem
🔎 full text search for 'exploding_gradient_problem'