Cell state
The cell state is an LSTM’s persistent memory representation, carried across sequence steps and updated through gates to retain information over time.
Sutskever's List
A cell state is the long-term memory pathway in an LSTM that carries information across time steps with selectively gated updates.
- How it is used
- Carries long-range information through LSTM sequences while gates regulate memory retention and exposure.
- How deep it goes
- Explains the carry pathway, its contrast with hidden state, and its three gating controls without deriving the update equations.
- Examples
- Uses the conveyor-belt analogy, long-sequence tasks, and standard and original LSTM cell schematics.
- What you can do after
- Understand how LSTMs preserve, update, and expose information across time steps.
Natural Language Processing in Action, Second Edition
A cell state is the persistent recurrent representation maintained by an LSTM across sequence positions.
- How it is used
- Carries long-term sequence information between LSTM time steps while the hidden state supplies each current output.
- How deep it goes
- Explains gate roles, state equations, and hidden-state interaction, but does not derive the learned weight matrices.
- Examples
- Uses token sequences, long documents, gate diagrams, and compact matrix equations to illustrate recurrent memory.
- What you can do after
- Understand how LSTMs preserve, update, and expose sequence information through a separate cell-state pathway.
Read how Natural Language Processing in Action, Second Edition explains cell state →
Deep Learning with R, Third Edition
A carry state is an information stream in an LSTM that transports a representation across sequence timesteps for later modification or use.
- How it is used
- Explains how LSTM cells preserve and update information across sequence timesteps.
- How deep it goes
- Descends to the LSTM carry equation and transformations, while stopping short of assigning fixed meanings to learned operations.
- Examples
- Uses an LSTM anatomy figure and pseudocode showing output, gate, and carry-state calculations.
- What you can do after
- Evaluate how an LSTM transports, forgets, and incorporates information through its carry pathway.
Read how Deep Learning with R, Third Edition explains cell state →
Deep Learning with Python, Third Edition
The LSTM internal state that transports information across timesteps to preserve long-term context.
- How it is used
- Preserves information across timesteps within an LSTM for modeling long-term sequence dependencies.
- How deep it goes
- Explains the carry update through input and forget gates, but stops short of implementation details.
- Examples
- Shows the carry track diagram and the gated pseudocode equation for updating c_t+1.
- What you can do after
- Evaluate/understand how LSTM gates retain, discard, and write information through the carry state.
Read how Deep Learning with Python, Third Edition explains cell state →
Inside Deep Learning: Math, Algorithms, Models
The LSTM memory state that carries longer-term information separately from the hidden state.
- How it is used
- Carries longer-term information in an LSTM, while the hidden state handles shorter-term work.
- How deep it goes
- Explains state roles and gate functions but provides no code or complete mathematical update equations.
- Examples
- Uses diagrams of sequential gates and their multiplication and addition operations.
- What you can do after
- Understand how forget, input, and output gates regulate information in the context state and hidden state.
Read how Inside Deep Learning: Math, Algorithms, Models explains cell state →
Also covered in
What to know first
- activation functionAn activation function transforms a neural-network unit’s input into its output, often introducing nonlinearity.
- gradientA gradient is the vector of partial derivatives of a scalar function with respect to its variables, indicating its local rate and direction of change.
- language modelingLanguage modeling is the task of learning or applying probability distributions over language sequences to estimate or predict units from context.
- linear layerA linear layer is a neural-network layer that applies a learned affine transformation to its input, typically using weights and a bias.
Related concepts
- LSTMpart of · A long short-term memory (LSTM) network is a recurrent neural-network architecture with gated memory cells that control information flow and model dependencies in sequential data.
- statekind of · State is information describing the condition or configuration of a system or computation at a particular time that may influence its behavior or subsequent transitions.
Questions about cell state
What is cell state?
The cell state is an LSTM’s persistent memory representation, carried across sequence steps and updated through gates to retain information over time.
Which Manning books explain cell state?
Sutskever's List, Natural Language Processing in Action, Second Edition, Deep Learning with R, Third Edition, Deep Learning with Python, Third Edition and Inside Deep Learning: Math, Algorithms, Models.
What should I know before learning cell state?
Manning books that teach cell state usually introduce activation function, gradient, language modeling and linear layer first.
What is cell state a kind of?
Cell state is a kind of state. State is information describing the condition or configuration of a system or computation at a particular time that may influence its behavior or subsequent transitions.
What is cell state part of?
Cell state is part of LSTM. A long short-term memory (LSTM) network is a recurrent neural-network architecture with gated memory cells that control information flow and model dependencies in sequential data.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.




