residual networks
Concept
A type of neural network architecture that employs residual connections to avoid vanishing gradients, crucial for enabling deeper networks.
Mentioned in 2 videos
Videos Mentioning residual networks
![[NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton](https://i.ytimg.com/vi/25FsKN0f8gQ/maxresdefault.jpg)
[NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton
Latent Space
A type of neural network architecture that employs residual connections to avoid vanishing gradients, crucial for enabling deeper networks.
Deep Learning for Computer Vision (Andrej Karpathy, OpenAI)
Lex Fridman
Architectures that enable training of much deeper networks by using skip connections and adding residuals, overcoming optimization issues found in 'plain' networks.