MIT 6S191: Recurrent Neural Networks Transformers and Attention

Learners: 325,973

Instructor: Alexander Amini

Duration:

This MIT 6S191 course provides an introduction to deep learning with a focus on recurrent neural networks, transformers, and attention. Lecturer Ava Amini will cover topics such as sequence modeling, neurons with recurrence, RNNs from scratch, design criteria for sequential modeling, backpropagation through time, long short term memory (LSTM), RNN applications, attention fundamentals, learning attention with neural networks, and scaling attention and applications. With all lectures, slides, and lab materials available online, this course is perfect for anyone looking to gain a better understanding of deep learning. Subscribe now to stay up to date with new deep learning lectures at MIT! ▼▲

Course Feature Course Overview Course Provider Discussion and Reviews

Go to class

Course Feature

Cost:

Free

Provider:

Youtube

Certificate:

No Information

Language:

English

Course Overview

❗The content presented here is sourced directly from Youtube platform. For comprehensive course details, including enrollment information, simply click on the 'Go to class' link on our website.

Updated in [July 21st, 2023]

MIT 6S191: Recurrent Neural Networks Transformers and Attention provides an introduction to deep learning. Lecturer Ava Amini will guide students through the lecture series, which covers sequence modeling, neurons with recurrence, recurrent neural networks, unfolding RNNs, design criteria for sequential modeling, word prediction examples, backpropagation through time, gradient issues, long short term memory (LSTM), RNN applications, attention fundamentals, intuition of attention, attention and search relationship, learning attention with neural networks, scaling attention and applications. All lecture slides and lab materials can be found at http://introtodeeplearning.com. Students are encouraged to subscribe to stay up to date with new deep learning lectures at MIT, or follow @MITDeepLearning on Twitter and Instagram to stay fully-connected.