ConceptAI & ML
Recurrent neural network
A type of neural network designed to process sequences by maintaining a hidden state that captures information from previous inputs.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Neural networks6Sequence2Dynamical system1Feed-forward neural network1Feedforward neural network1Neural network training1Non-linearities1Sequence modeling1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
7Each in their own terms, from the easiest level.
Brian Yu
A neural network that generates output that gets fed back into itself as input for future runs of the network.Fei-Fei Li, Justin Johnson & Serena Yeung
A neural network architecture designed to process sequential data of variable length by maintaining a hidden state across steps.Ava Amini
Neural networks comprising recurrent cells that use a recurrence relation to capture cyclic temporal dependencies in sequential data.Russ Tedrake
A neural network where the output of a neuron is looped back into its input.Steven Feng
Sequence models that process inputs step by step while maintaining a hidden state that carries information forward through time.Ellie Pavlick
A neural network architecture for sequence modeling where processing time flows sequentially from left to right.
Lectures that assume it
10- Detection and Segmentation
- DeepMind's Perceiver and Perceiver IO: New data family architecture
- The Deep Learning Revolution (Turing Award Lecture)
- Harnessing Chaos and Predicting the Unpredictable with Artificial Intelligence
- Model-Based Reinforcement Learning with Policies
- Deep Reinforcement Learning
- Transfer Learning: Data
- Super Turing Computing: Foundations for Aware and Ever-Adapting Systems
- Reasonable AI
- Neuroscience-Inspired Artificial Intelligence
Connections
26The lectures that define it or assume it, and the concepts next to it.
Concepts9
- Neural networks
- Sequence
- Dynamical system
- Feed-forward neural network
- Backpropagation through time
- Attention mechanism
Show 3 moreShow fewer
Lectures17
- Harvard CS50’s Artificial Intelligence with Python – Full University Course
- Architectures: Memory
- Recurrent Neural Networks
- Recurrent Neural Networks, Transformers, and Attention
- Nonlinear Dynamics
- Symbols and Grounding in Large Language Models
Show 11 moreShow fewer
- Overview of Transformers (Stanford CS25: Transformers United V6)
- Detection and Segmentation
- DeepMind's Perceiver and Perceiver IO: New data family architecture
- The Deep Learning Revolution (Turing Award Lecture)
- Harnessing Chaos and Predicting the Unpredictable with Artificial Intelligence
- Model-Based Reinforcement Learning with Policies
- Deep Reinforcement Learning
- Transfer Learning: Data
- Super Turing Computing: Foundations for Aware and Ever-Adapting Systems
- Reasonable AI
- Neuroscience-Inspired Artificial Intelligence