Landmark 2 stops to get here · leads to 6

Recurrent Neural Network

A neural network architecture with loops that allow information to persist, designed for sequential data like text and time series.

Your route here

2 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Neural Network ✓ understood

    A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

  3. Recurrent Neural Network · you are here ✓ understood

Picture it

  1. 01 x₁ → h₁ Read the first input, produce a hidden state
  2. 02 x₂ + h₁ → h₂ Combine the next input with the previous state
  3. 03 x₃ + h₂ → h₃ Same weights reused at every time step
  4. 04 Output from hₜ The final state summarizes the whole sequence
This is the RNN's loop unrolled over time: the hidden state carries memory forward, one step at a time, with the same weights at each step.

Where it sits

Before this

Neural Network
Recurrent Neural Network

Leads to

Gated Recurrent Unit Long Short-Term Memory Sequence-to-Sequence CTC Loss Echo State Network Liquid State Machine

Explore nearby

Neural Networks Long Short-Term Memory A type of RNN architecture with gates that can learn long-term dependencies, solving the vanishing gradient problem. Neural Networks Gated Recurrent Unit A simplified variant of LSTM with fewer parameters, using an update gate and a reset gate to control information flow. Language & LLMs Sequence-to-Sequence Models that transform input sequences to output sequences, used for translation, summarization, and generation. Training Vanishing Gradient A problem where gradients become extremely small during backpropagation, preventing deep networks from learning effectively. Language & LLMs Transformer A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model.

In the research

All papers →

4 papers that build on Recurrent Neural Network .