recurrent neural network
A type of neural network designed to handle sequential data by maintaining a hidden state (memory) across time steps, improving on simpler models for handling dependencies.
Videos Mentioning recurrent neural network
![2024 in Post-Transformer Architectures: State Space Models, RWKV [Latent Space LIVE! @ NeurIPS 2024]](https://i.ytimg.com/vi/LPe6iC73lrc/maxresdefault.jpg)
2024 in Post-Transformer Architectures: State Space Models, RWKV [Latent Space LIVE! @ NeurIPS 2024]
Latent Space
An older architecture from which RWKV draws inspiration, highlighting its scalability issues on GPUs compared to parallelizable attention mechanisms.
Andrew Ng: Deep Learning, Education, and Real-World AI | Lex Fridman Podcast #73
Lex Fridman
A type of neural network that processes sequential data, mentioned as a key concept taught in the Deep Learning Specialization.
AI Language Models & Transformers - Computerphile
Computerphile
A type of neural network designed to handle sequential data by maintaining a hidden state (memory) across time steps, improving on simpler models for handling dependencies.
MIT 6.S094: Deep Reinforcement Learning for Motion Planning
Lex Fridman
A type of neural network with memory that can retain information about the temporal dynamics of data, but is often more difficult to train.
Theano Tutorial (Pascal Lamblin, MILA)
Lex Fridman
Mentioned in the context of models generating sequences that require loop-like structures, addressed by Theano's 'scan' function.