LSTM
artificial recurrent neural network architecture used in deep learning
Common Themes
Videos Mentioning LSTM

Breaking down the OG GPT Paper by Alec Radford
Latent Space
An alternative architecture to Transformers, which GPT-1 showed superior performance against.
![[Paper Club] BERT: Bidirectional Encoder Representations from Transformers](https://i.ytimg.com/vi/V64q3p7DNjc/maxresdefault.jpg)
[Paper Club] BERT: Bidirectional Encoder Representations from Transformers
Latent Space
Long Short-Term Memory, a type of RNN architecture, mentioned as pre-Transformer technology.

A Comprehensive Overview of Large Language Models - Latent Space Paper Club
Latent Space
Long Short-Term Memory, a type of RNN designed to handle long-range dependencies.

Jeff Dean’s Lecture for YC AI
Y Combinator
A type of recurrent neural network architecture used in deep learning, mentioned in the context of translation models.

Making Music and Art Through Machine Learning - Doug Eck of Magenta
Y Combinator
Long Short-Term Memory, a type of recurrent neural network known for its ability to learn long-term dependencies, discussed in the context of its history and development.

Yoshua Bengio: Deep Learning | Lex Fridman Podcast #4
Lex Fridman
Mentioned as a current architecture in artificial neural networks that is not fully capable of capturing very long-term credit assignment as humans can.

Ian Goodfellow: Generative Adversarial Networks (GANs) | Lex Fridman Podcast #19
Lex Fridman
Long Short-Term Memory networks, designed for handling sequential data but still not fully replicating human short-term memory.

Deep Learning Basics: Introduction and Overview
Lex Fridman
Long Short-Term Memory networks, a type of RNN that addresses the vanishing gradient problem and can learn long-term dependencies.

Deep Learning State of the Art (2019)
Lex Fridman
A type of recurrent neural network unit mentioned in the context of encoder-decoder architectures and Elmo.

After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Latent Space
A type of recurrent neural network (RNN) used in early language modeling and combined with CNNs for image captioning tasks.

AI Language Models & Transformers - Computerphile
Computerphile

MIT AGI: Artificial General Intelligence
Lex Fridman
Long Short-Term Memory networks, a type of recurrent neural network, mentioned as being used to control the 26 facial muscles for generating emotions in the 'Angel' project.

Deep Learning for Natural Language Processing (Richard Socher, Salesforce)
Lex Fridman
Long Short-Term Memory, a type of recurrent neural network unit that is more advanced and influential than GRUs. A lecture by Kwok on LSTMs is mentioned.