Dropout
regularization method for artificial neural networks
Build a research pod on Dropout.
6 expert discussions. Save them all to your own pod, ask any question, get cited answers.
Common Themes
Videos Mentioning Dropout
Let's build GPT: from scratch, in code, spelled out.
Andrej Karpathy
Regularization technique used in the scaled-up model to reduce overfitting (randomly disables activations during training).
Jeremy Howard: fast.ai Deep Learning Courses and Research | Lex Fridman Podcast #35
Lex Fridman
A regularization technique for neural networks that prevents overfitting, cited as a breakthrough not requiring multiple GPUs.
Deep Learning Basics: Introduction and Overview
Lex Fridman
A regularization technique where random neurons are ignored during training to prevent overfitting, mentioned as an idea used in AlexNet.
Deep Learning for Computer Vision (Andrej Karpathy, OpenAI)
Lex Fridman
A regularization technique that randomly sets a proportion of neurons to zero during training to prevent overfitting.
Foundations of Deep Learning (Hugo Larochelle, Twitter)
Lex Fridman
A regularization technique where hidden units are randomly ignored during training to prevent co-adaptation and overfitting.
Stanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 1 - Transformers
Stanford Online
تقنية تستخدم لحذف بعض الوحدات عمدًا أثناء التدريب لمنع النموذج من الاعتماد بشكل كبير على ميزات معينة وتحسين التعميم.