liveBook · Manning

Gating

As explained in Build AI Drug Discovery Pipelines

Recurrent gating is the controlled regulation of information retained, forgotten, or incorporated by a recurrent neural-network state.

Gating regulates the information retained, forgotten, or incorporated into a recurrent neural-network state. In molecular generation, it helps preserve long-range dependencies needed for valid SMILES, including ring closures, parentheses, and global valence consistency. section 10.4.2

A gated recurrent unit uses two filters:

  • The reset gate controls how much of the previous hidden state contributes to the candidate state. section 10.4.2
  • The update gate controls how much of the candidate state replaces the previous hidden state. section 10.4.2
  • This selective information flow improves long-range dependency handling compared with a simple RNN, but increases computation and memory requirements. section 10.4.2

Molecular sequence memory

When processing benzene as "c1ccccc1" or a longer molecule such as "CC(C)CC(=O)NC1=CC=C(C=C1)O", gating helps retain information about openings that must later be closed correctly. section 10.4.2

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains gate roles, state equations, internal weight matrices, and a PyTorch GRU cell implementation.
Examples
Uses benzene and a longer molecular SMILES string to illustrate distant ring closures, parentheses, and structural consistency.
What you can do after
Build it from scratch with PyTorch by implementing reset, update, candidate-state, and hidden-state computations.
How it connects
Connects recurrent neural networks, gated recurrent units, vanishing gradients, SMILES, and long-range dependencies.

Also explained in

Compare how 6 books explain gating →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.