Reset gate

As explained in Graph Neural Networks in Action

A gated recurrent unit component that controls how much prior hidden-state information is discarded when computing a new state.

A reset gate is a gated recurrent unit component that controls how much prior hidden-state information is discarded when forming a new state. It helps a GRU forget information that is no longer useful while modeling sequential data. section 6.5.1

Understand the gate as part of a GRU state-update pipeline:

• Read the current input and previous hidden state. section 6.5.1
• Use the reset gate to determine how much previous information should be forgotten. section 6.4.2
• Combine the resulting information with a candidate activation to produce the actual hidden state; the update gate separately controls how much state changes. section 6.5.1

Resetting state in a graph decoder

In a neural relational inference decoder, a custom GRU processes node inputs and aggregated edge messages. Its hidden state represents node information, while reset gating determines how much prior node state is erased before predicting future frames. section 6.4.2

Figure 6.18 Design of the GRU layer, where r_t represents the reset gate, z_t is the update gate, ~h_t is the candidate function, and h_t is the final actual hidden state

Use the GRU design diagram to distinguish the reset gate from the update gate, candidate activation, and final hidden state. section 6.5.1

How Graph Neural Networks in Action covers it

How deep it goes

Explains the gate’s forgetting role and GRU context, but stops short of deriving its activation equations.

Examples

Uses pose-sequence GRUs and a neural relational inference decoder with node states, edge messages, and future-frame predictions.

What it assumes

Assumes basic recurrent neural network and hidden-state terminology while introducing GRU gates and candidate activations.

What you can do after

Apply via PyTorch by configuring a GRU or custom GRU for sequential or graph-based state updates.

How it connects

Connects reset gates to gated recurrent units, recurrent neural networks, update gates, candidate activation, hidden states, and neural relational inference.

liveBookmanning.com

Read Graph Neural Networks in Action on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA reset gate is a gated recurrent mechanism that controls which portions of the previous hidden state are discarded as irrelevant to the current output.

Compare how 2 books explain reset gate →

Related concepts

• GRUpart of · A gated recurrent unit (GRU) is a recurrent neural-network architecture that uses learned gates to regulate information flow and update a hidden state across sequence steps.
• sigmoiduses · A sigmoid is a smooth, bounded, S-shaped function that maps real-valued inputs between two limiting values, commonly zero and one.
• forget gatecontrasts with · A forget gate is an LSTM component that controls how much information from the previous cell state is retained or discarded.
• gated updatecontrasts with · A gated update is a state or representation update in which learned gates control how new information is combined with or replaces existing information.

This explainer was generated by Manning's knowledge graph from the text of Graph Neural Networks in Action. The section links point to the parts of the book it draws on.