MNIST
A classic handwritten digit dataset, used as an example to illustrate how benchmarks can have mislabeled examples, making 100% accuracy indicative of a flaw.
Videos Mentioning MNIST
State of the Art: Training 70B LLMs on 10,000 H100 clusters
Latent Space
A classic handwritten digit dataset, used as an example to illustrate how benchmarks can have mislabeled examples, making 100% accuracy indicative of a flaw.
Deep Learning Basics: Introduction and Overview
Lex Fridman
A dataset of handwritten digits frequently used for training and testing image classification models, mentioned as a key development in the 70s/80s.
TensorFlow Tutorial (Sherry Moore, Google Brain)
Lex Fridman
A widely used dataset of handwritten digits used for training and testing image classification models.
Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGI | Lex Fridman Podcast #333
Lex Fridman
A classic dataset of handwritten digits, now considered a 'joke dataset' for modern machine learning research because it's been 'crushed' by current algorithms.