Neural network
A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
Build AI Drug Discovery Pipelines
An artificial neural network is a parameterized computational model composed of interconnected units arranged in layers.
- How it is used
- Uses neural networks for molecular activity prediction in ligand-based virtual screening.
- How deep it goes
- Explains computational graphs, weights, loss, and gradients alongside a PyTorch workflow, without comprehensive PyTorch coverage.
- Examples
- Demonstrates EGFR pIC50 prediction and compares neural-network performance on RNA-binding classification with a tree-based model.
- What you can do after
- Apply a neural network via PyTorch to train and evaluate a molecular activity predictor.
Read how Build AI Drug Discovery Pipelines explains neural network →
Timeless Algorithms, The Foundational Ideas
A neural network is a parameterized computational model composed of interconnected layers that transform inputs through learned functions.
- How it is used
- Explains how multilayer models learn representations and make predictions from data.
- How deep it goes
- Traces the forward pass, loss, backpropagation, and parameter updates, then examines optimization and generalization limits.
- Examples
- Uses a feedforward-network diagram and contrasts regression outputs with binary and multiclass predictions.
- What you can do after
- Evaluate and understand neural-network predictions, training objectives, and limitations rather than treat the model as a black box.
Read how Timeless Algorithms, The Foundational Ideas explains neural network →
Machines that Think
A computational model composed of interconnected units with parameters that can be learned to process patterns.
- How it is used
- Explains how adaptive AI systems turn data into representations and produce behavior across different tasks.
- How deep it goes
- Explains interconnected computations, parameter updates, batches, and generalization without a code implementation.
- Examples
- Uses visual features from edges to objects and word relationships in mathematical space to illustrate learned representations.
- What you can do after
- Evaluate and understand neural-network behavior by distinguishing generalization from memorization and observable performance from underlying mechanism.
Transfer Learning for Natural Language Processing
A neural network is a computational model composed of interconnected units whose parameters are adjusted to learn patterns from data.
- How it is used
- Introduces neural networks as a machine-learning approach used for recognition and natural language processing.
- How deep it goes
- Outlines gradient-based training and illustrates a feedforward architecture, while deferring further review of training concepts.
- Examples
- Uses handwritten-digit recognition and a word-embedding analogy to illustrate neural-network applications.
- What you can do after
- Understand how neural networks are trained and how their embeddings can represent relationships between words.
Read how Transfer Learning for Natural Language Processing explains neural network →
Grokking Bayes
A neural network is a machine learning model composed of interconnected parameterized units that transform inputs into predictions.
- How it is used
- Uses layered transformations to learn complex input-to-output mappings and make predictions.
- How deep it goes
- Defines layers, activations, nodes, edges, weights, biases, and hidden-layer choices, but stops short of training procedures.
- Examples
- Uses a noisy sine-function data set, a two-hidden-layer architecture, and adversarial image noise to illustrate predictions and failure.
- What you can do after
- Evaluate a network’s architecture, parameters, predictions, and vulnerability to confident errors without uncertainty modeling.
Applied Reinforcement Learning
A neural network is a parameterized computational model composed of interconnected transformations that map inputs to outputs.
- How it is used
- Replaces tabular Q-tables with parameterized functions that generalize across states.
- How deep it goes
- Details stacked transformations, activations, backpropagation, and typical hidden-layer counts.
- Examples
- Illustrates DQN action-value estimates and a PPO portfolio policy over eight allocation choices.
- What you can do after
- Understand how networks represent RL functions and when deeper architectures suit high-dimensional inputs.
Read how Applied Reinforcement Learning explains neural network →
Local Image Generation
A neural network is a machine-learning model composed of interconnected computational units that transform inputs through weighted operations and activation functions.
- How it is used
- Positions neural networks as the specific machine-learning mechanism underlying major Stable Diffusion components.
- How deep it goes
- Explains weighted inputs and activation through a hand-worked AND detector, then stops short of detailed training mechanics.
- Examples
- Uses a two-input AND detector, binary on/off values, weighted sums, activation outputs, and Stable Diffusion denoising.
- What you can do after
- Evaluate how weights and activation functions turn inputs into outputs and identify their role in Stable Diffusion models.
Bayesian Optimization in Action
A neural network is a machine-learning model composed of interconnected computational layers that transform inputs into outputs.
- How it is used
- Uses neural networks to extract features from complex structured data before Gaussian-process similarity modeling.
- How deep it goes
- Explains layered matrix computations, nonlinear activations, and feature extraction, but defers thorough neural-network treatment.
- Examples
- Uses housing-price similarity, front-door color, structured inputs, and layered-computation diagrams as teaching examples.
- What you can do after
- Evaluate neural networks as flexible feature extractors for Gaussian-process models of structured data.
Read how Bayesian Optimization in Action explains neural network →
Designing Deep Learning Systems: A guide for software engineers
A computational model composed of interconnected parameterized units that learns mappings from inputs to outputs.
- How it is used
- Positions neural networks as programmable algorithms inside deep-learning systems that learn from data and make decisions.
- How deep it goes
- Defines the model’s learning role and highlights parameter-scale constraints, but defers algorithmic internals and mathematical derivations.
- Examples
- Uses chatbots, assistive driving, road-marking perception, and increasingly large image-classification networks as examples.
- What you can do after
- Evaluate how neural-network size affects GPU fit and recognize when distributed-training strategies become relevant.
Read how Designing Deep Learning Systems: A guide for software engineers explains neural network →
Demand Forecasting Best Practices
A neural network is a computational model composed of interconnected parameterized units organized in layers that transform inputs into outputs.
- How it is used
- Explains neural networks as a machine-learning model for transforming numerical inputs into predictions.
- How deep it goes
- Explains neurons, activation functions, weights, layers, forward propagation, and training, but does not detail the optimization procedure.
- Examples
- Uses four input features, two forecast periods, artificial-neuron and network figures, and a timeline reaching back to 1957.
- What you can do after
- Evaluate/understand how layered neurons convert features into predictions and why network shape and activation functions matter.
Read how Demand Forecasting Best Practices explains neural network →
Ensemble Methods for Machine Learning
A neural network is a parameterized computational model composed of connected units that transform inputs through learned weights and nonlinear functions.
- How it is used
- Uses layered feature construction to model nonlinear relationships with continuous labels.
- How deep it goes
- Explains layers, depth, induced feature combinations, and learned weights, but does not develop neural-network training internals.
- Examples
- Uses a noisy damped-sinusoid data set, MLPRegressor code, and a decision-tree performance comparison.
- What you can do after
- Apply it via scikit-learn's MLPRegressor and evaluate predictions with MSE and MAD.
Read how Ensemble Methods for Machine Learning explains neural network →
Also covered in
- Regular Expression Puzzles and AI Coding Assistants
- Julia as a Second Language
- Build Applications with Local AI Models on a Mac
- CUDA for LLMs
What to know first
- machine learningMachine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
- artificial intelligenceArtificial intelligence is the field of computing concerned with creating systems that perform tasks associated with intelligence, such as learning, reasoning, perception, and decision-making.
- deep learningDeep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
- objective functionAn objective function is a mathematical function that assigns values to candidate solutions or parameter settings, which an optimization procedure seeks to minimize or maximize.
Related concepts
- deep learningused by · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
- AI modelkind of · An AI model is a computational system that learns or encodes patterns to map inputs to outputs such as predictions, classifications, or generated content.
- autoencoderincludes · An autoencoder is a neural network that encodes input data into an internal representation and decodes it to reconstruct the input or an approximation.
- machine learningkind of · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
- recurrent neural networkincludes · A recurrent neural network is a neural network that processes ordered inputs while carrying and updating an internal state across successive steps.
- large language modelincludes · A large language model is a machine-learning model trained on extensive text data to process and generate natural language.
Questions about neural network
What is neural network?
A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
Which Manning books explain neural network?
Build AI Drug Discovery Pipelines, Timeless Algorithms, The Foundational Ideas, Machines that Think, Transfer Learning for Natural Language Processing, Grokking Bayes, Applied Reinforcement Learning, Local Image Generation, Bayesian Optimization in Action and 3 more.
What should I know before learning neural network?
Manning books that teach neural network usually introduce machine learning, artificial intelligence, deep learning and objective function first.
What kinds of neural network are there?
Kinds of neural network include autoencoder, recurrent neural network and large language model.
What is neural network a kind of?
Neural network is a kind of AI model. An AI model is a computational system that learns or encodes patterns to map inputs to outputs such as predictions, classifications, or generated content.
What is neural network also called?
Neural network is also called neural nets.
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.










