MIT Introduction to Deep Learning 6.S191: Lecture 1
*New 2026 Edition*
Foundations of Deep Learning
Lecturer: Alexander Amini

For all lectures, slides, and lab materials: http://introtodeeplearning.com/

Subscribe to stay up to date with new deep learning lectures at MIT, or follow us on @MITDeepLearning on Twitter and Instagram to stay fully-connected!!

YouTube

MIT 6.S191 is a one-week deep learning boot camp covering fundamentals through modern advances. The first lecture introduces core concepts: the perceptron (dot product + bias + activation function), building multi-layer neural networks, forward and back propagation, gradient descent and its variants (SGD, mini-batch, Adam), loss functions for classification and regression, and regularization techniques including dropout and early stopping. Practical code examples are shown in both TensorFlow and PyTorch. The lecture also contextualizes the rapid pace of AI progress, from 2015 facial generation to on-device LLMs outperforming the original GPT-4.

MIT Introduction to Deep Learning | 6.S191