liveBook · Manning

Neuron

Also called units

A neuron is a computational unit in a neural network that transforms input signals, typically using learned parameters and an activation function, to produce an output.

How 10 Manning books explain it

Natural Language Processing in Action, Second Edition

An artificial neuron is a parameterized computational unit that combines inputs to produce an output, typically through an activation function.

How it is used
Builds intuition for language-processing neural networks from a single predictive unit.
How deep it goes
Works through weighted sums, activation and a trainable single-neuron implementation.
Examples
Uses word counts and first-name character features to demonstrate neuron predictions.
What you can do after
Apply a single logistic neuron via PyTorch to a binary classification task.

Read how Natural Language Processing in Action, Second Edition explains neuron →

Classic Computer Science Problems in Swift: Essential techniques for practicing programmers

A neuron is a computational unit that combines input signals with weights, applies an activation function, and produces an output signal.

How it is used
Models the weighted signal-processing unit used to build and train a feed-forward classification network.
How deep it goes
Defines the computation and implements neuron state and training support, while deferring dot-product fundamentals and calculus derivations.
Examples
Uses Swift neuron and layer code plus an iris classifier with four inputs, six hidden neurons, and three outputs.
What you can do after
Build it from scratch as a Swift neuron that produces activated outputs and retains state for backpropagation.

Read how Classic Computer Science Problems in Swift: Essential techniques for practicing programmers explains neuron →

Grokking AI Algorithms, Second Edition

A neural-network node is a computational unit that combines weighted signals and transforms them into an activation.

How it is used
Uses the neuron as the building block for perceptrons and multilayer networks that make predictions.
How deep it goes
Explains weighted sums and activations step by step, extending individual calculations to matrix multiplication for a hidden layer.
Examples
Uses apartment rental prediction and a car-collision network with speed, terrain, vision, and driving experience inputs.
What you can do after
Evaluate/understand how weighted inputs become neuron activations and flow through a trained network to a prediction.

Read how Grokking AI Algorithms, Second Edition explains neuron →

Build AI Drug Discovery Pipelines

An artificial neuron is a computational unit that transforms weighted inputs, usually with a bias and activation function, into an output.

How it is used
Uses neurons as the basic units for constructing trainable neural networks and computational graphs.
How deep it goes
Explains inputs, weights, bias, activations, gradients, and stacking, but stops short of detailed neuron-level derivations.
Examples
Demonstrates a PyTorch logistic unit with three inputs, explicit weights and bias, sigmoid output, binary cross-entropy, and gradients.
What you can do after
Build it from scratch by implementing a weighted forward pass, selecting an activation, computing loss, and obtaining parameter gradients.

Read how Build AI Drug Discovery Pipelines explains neuron →

Machines that Think

A computational unit in a neural network that transforms incoming signals and passes an output to other units.

How it is used
Explains the computational building block of neural networks and its role in comparing artificial systems with biological cognition.
How deep it goes
Explains weighted inputs, bias, activation, and output, then examines trainability and the simplifications made relative to biological neurons.
Examples
Illustrates neuron structure with a computation diagram and network organization with an email classification example.
What you can do after
Evaluate and understand how simple units contribute to network behavior without assuming biological equivalence.

Read how Machines that Think explains neuron →

Optimization Algorithms: AI techniques for design, planning, and control problems

An artificial neuron is a computational unit that combines weighted inputs and a bias before applying an activation function to produce an output.

How it is used
Explains the basic computational unit used to construct neural networks for classification and other machine-learning mappings.
How deep it goes
Defines weighted inputs, bias, threshold, and output, then illustrates layer computation without developing neuron-level training mathematics.
Examples
Uses vehicle-image object recognition and a Python penguins classifier with four inputs, ten hidden neurons, and three output classes.
What you can do after
Evaluate/understand how weighted inputs and biases become layer activations in a small neural-network classifier.

Read how Optimization Algorithms: AI techniques for design, planning, and control problems explains neuron →

Data Without Labels

A neuron is a computational unit in a neural network that combines inputs and applies an activation function to produce an output.

How it is used
Uses neurons as the input-processing units that pass information through a neural network toward a prediction.
How deep it goes
Explains numerical inputs, weights, weighted sums, activation, and layered connections; does not work through a numerical calculation.
Examples
Illustrates neurons with a face-identification network, layer diagrams, and localized connections in image classification.
What you can do after
Evaluate/understand it: trace how a neuron transforms inputs and passes its output toward a network prediction.

Read how Data Without Labels explains neuron →

Sutskever's List

A computational unit in a neural network that combines weighted inputs and applies an activation function.

How it is used
Defines the computational unit used to describe AlexNet’s network architecture and its biological framing.
How deep it goes
Explains weighted inputs, optional bias, and activation, then notes why counts become ambiguous in convolutional layers.
Examples
Uses AlexNet’s roughly 650,000 neurons and 60 million parameters to contrast two architectural counts.
What you can do after
Evaluate neuron counts as architectural descriptors and distinguish them from parameter counts when comparing models.

Read how Sutskever's List explains neuron →

Rearchitecting LLMs

A neuron is a computational unit in a neural network that transforms inputs using learned parameters and a nonlinear activation.

How it is used
Targets intermediate MLP neurons for fine-grained width pruning.
How deep it goes
Defines neurons as projection-matrix rows and details weight-range scoring alongside activation-calibrated selection.
Examples
Uses weight-range comparisons and contrasts WikiText- and SMS-calibrated neuron selection.
What you can do after
Apply width pruning by scoring paired projections, selecting neurons, and rebuilding smaller Linear layers while preserving module boundaries.

Read how Rearchitecting LLMs explains neuron →

Timeless Algorithms, The Foundational Ideas

A neuron is a computational unit in a neural network that combines inputs and produces an output.

How it is used
Transforms incoming numerical values into an output passed to the next layer.
How deep it goes
Defines weighted summation, bias, and activation, then connects node outputs to representations and training updates.
Examples
Uses pixel values, sensor readings, customer features, and word embeddings as examples of network inputs.
What you can do after
Understand how a neuron combines inputs and how its output contributes to a network prediction.

Read how Timeless Algorithms, The Foundational Ideas explains neuron →

Also covered in

What to know first

Related concepts

Questions about neuron

What is neuron?

A neuron is a computational unit in a neural network that transforms input signals, typically using learned parameters and an activation function, to produce an output.

Which Manning books explain neuron?

Natural Language Processing in Action, Second Edition, Classic Computer Science Problems in Swift: Essential techniques for practicing programmers, Grokking AI Algorithms, Second Edition, Build AI Drug Discovery Pipelines, Machines that Think, Optimization Algorithms: AI techniques for design, planning, and control problems, Data Without Labels, Sutskever's List and 2 more.

What should I know before learning neuron?

Manning books that teach neuron usually introduce language model, sigmoid, linear regression and machine learning first.

What kinds of neuron are there?

Kinds of neuron include perceptron.

What is neuron part of?

Neuron is part of neural network layer. A neural network layer is a computational component or stage that transforms inputs into outputs within a neural network.

What is neuron also called?

Neuron is also called units.

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.