Deep learning
Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
A machine learning approach based on neural networks with multiple learned layers of representation.
- How it is used
- Supports selecting, building, and comparing neural-network solutions for tabular business prediction problems.
- How deep it goes
- Explains preprocessing, Keras model definition, callback-controlled training, and evaluation while deferring detailed research surveys and neural-network internals.
- Examples
- Uses Airbnb price prediction and Kuala Lumpur real-estate price classification, with a Tokyo Airbnb regression comparison.
- What you can do after
- Apply it via Keras to prepare tabular data, train a classifier with callbacks, and evaluate it against test data.
Read how Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI explains deep learning →
Inside AI
A deep neural network is a neural network containing multiple hidden layers that learn hierarchical representations from simpler features.
- How it is used
- Introduces deep learning as a pattern-recognition approach for complex data and a component of generative AI.
- How deep it goes
- Explains hidden layers, hierarchical representations, weights, and backpropagation without developing the underlying theory.
- Examples
- Illustrates image recognition with cats and speech recognition with Siri’s wake phrase.
- What you can do after
- Evaluate/understand deep learning applications against data requirements, training costs, generalization limits, and claims of intelligence.
Grokking Machine Learning, Second Edition
A field of machine learning that uses neural networks.
- How it is used
- Uses neural networks for difficult classification and regression tasks, especially image recognition and text processing.
- How deep it goes
- Builds from perceptrons and layered boundaries through backpropagation, overfitting, and Keras implementations.
- Examples
- Uses alien sentiment data, a circular two-feature dataset, and MNIST handwritten digits.
- What you can do after
- Apply it via Keras to train neural-network classifiers on nonlinear data and handwritten images.
Read how Grokking Machine Learning, Second Edition explains deep learning →
Build AI Drug Discovery Pipelines
A deep neural network is a neural network composed of multiple computational layers that learn hierarchical representations from data.
- How it is used
- Applies deep learning to drug-discovery tasks, including virtual screening and synthesis planning.
- How deep it goes
- Introduces deep learning and outlines a PyTorch screening workflow, deferring detailed implementation from the initial overview.
- Examples
- Uses kinase-targeted compound screening and synthesis planning to illustrate applications.
- What you can do after
- Apply deep learning via PyTorch to fit, evaluate, and save a screening model.
Read how Build AI Drug Discovery Pipelines explains deep learning →
Data Without Labels
A deep learning model is a machine-learning model composed of multiple layers of learned representations.
- How it is used
- Applies neural networks to recognition, prediction, and pattern discovery, especially with unstructured data.
- How deep it goes
- Explains network components and supervised training through loss and backpropagation, then introduces unlabeled training methods.
- Examples
- Uses labeled face identification and contrasts supervised image classification with unsupervised image grouping.
- What you can do after
- Evaluate/understand it by matching network approaches to data and checking data quality and processing capacity before use.
Outlier Detection in Python
Deep learning is machine learning based on neural networks with multiple computational layers that learn hierarchical representations.
- How it is used
- Applies deep neural networks to outlier detection, especially for image, video, and audio data where other viable options are limited.
- How deep it goes
- Explains layer-by-layer prediction and surveys image-detection approaches, but does not specify training procedures or implementations in the supplied evidence.
- Examples
- Uses image classification, low-confidence bird classifications, and rotated images to illustrate predictions and potential outlier signals.
- What you can do after
- Evaluate/understand it by comparing image-outlier signals and weighing deep learning’s data, speed, tuning, and tabular-data trade-offs.
Read how Outlier Detection in Python explains deep learning →
Designing Deep Learning Systems: A guide for software engineers
A machine learning model that uses multiple layers of learned representations to make predictions or decisions.
- How it is used
- Connects model development to product requirements, production pipelines, serving, and collaboration across engineering roles.
- How deep it goes
- Details data exploration, training, inference, packaging, and serving constraints while deferring individual component implementations.
- Examples
- Uses natural-language customer support, visual recognition with ImageNet, JupyterLab notebooks, and experimental-model metric comparisons.
- What you can do after
- Evaluate/understand how to move a trained model from iterative prototyping into a production system.
Read how Designing Deep Learning Systems: A guide for software engineers explains deep learning →
Transfer Learning for Natural Language Processing
Deep learning is a machine-learning approach that uses neural networks with multiple layers to learn representations from data.
- How it is used
- Situates deep learning within AI and NLP while motivating learned features and transfer learning.
- How deep it goes
- Explains layered representations, weights, and backpropagation at a conceptual level without a training implementation.
- Examples
- Uses sentiment classification, ImageNet object recognition, and word2vec embeddings as examples.
- What you can do after
- Evaluate and understand deep learning’s role in NLP and transfer learning.
Read how Transfer Learning for Natural Language Processing explains deep learning →
Hidden Influences
A machine learning approach that uses multilayered neural networks to learn hierarchical representations from data.
- How it is used
- Supports data-driven recommendations by learning patterns from platform behavior.
- How deep it goes
- Explains layered feature discovery and embeddings, while noting that human-readable explanations remain an open problem.
- Examples
- Uses login times and user-item ratings to illustrate learned representations and the limits of simpler recommendation data.
- What you can do after
- Evaluate and understand how learned representations support recommendations and why their decisions can be hard to explain.
Evolutionary Deep Learning: Genetic algorithms and neural networks
A deep learning model is a neural network with multiple learned layers that learns hierarchical representations from data.
- How it is used
- Frames deep learning as a system to develop, tune, and automate for AI and machine-learning tasks.
- How deep it goes
- Works through hyperparameter experiments and MNIST training, while deferring basic deep-learning principles to prior knowledge.
- Examples
- Uses PyTorch function approximation and TensorFlow/Keras MNIST handwritten-digit classification with evolutionary optimization.
- What you can do after
- Apply it via PyTorch or Keras to train models, vary hyperparameters, and inspect fit, accuracy, and classification reports.
Read how Evolutionary Deep Learning: Genetic algorithms and neural networks explains deep learning →
Timeless Algorithms, The Foundational Ideas
Deep learning is a machine-learning paradigm that learns representations through multiple parameterized computational layers.
- How it is used
- Frames deep learning as a way to learn representations directly from data for prediction and pattern recognition.
- How deep it goes
- Explains layer transformations and the training cycle through loss, backpropagation and gradient descent, alongside generalization constraints.
- Examples
- Uses image recognition, speech processing and classification and regression predictions to illustrate applications and outputs.
- What you can do after
- Evaluate and understand how learned representations, training decisions and generalization constraints affect deep-learning predictions.
Read how Timeless Algorithms, The Foundational Ideas explains deep learning →
Grokking AI Applications
Deep learning is machine learning based on training neural networks with many computational layers to learn hierarchical data representations.
- How it is used
- Uses deep neural networks to calculate GPT-3 prompt context while accounting for word positions.
- How deep it goes
- Defines neurons, layered connections, and hierarchical representations, then links positional context to transformers and attention.
- Examples
- Contrasts the contexts of “The dog bit the man” and “The man bit the dog.”
- What you can do after
- Understand how layered networks can account for word positions when calculating language context.
Effective Data Analysis
Deep learning is a machine-learning approach that uses multilayered neural networks to learn representations and patterns from data.
- How it is used
- Deploys neural networks to automate categorization and other repetitive decisions in operational workflows.
- How deep it goes
- Defines pattern-based automation and illustrates it with ticket categorization, but stops short of training or implementation details.
- Examples
- Uses automated support-ticket categorization by priority and type as its concrete example.
- What you can do after
- Evaluate automated categorization systems for efficiency gains and potential bias in their data-driven decisions.
Vibe Engineering
Deep learning is a machine-learning approach based on multilayer neural networks that learn hierarchical representations from data.
- How it is used
- Applies deep learning to classify high-risk medicines from descriptions, side effects, and drug-interaction data.
- How deep it goes
- Builds a text-classification workflow with labeling, training, confusion-matrix evaluation, and threshold trade-offs, while deferring neural internals.
- Examples
- Uses a medicine-risk classifier, class counts, epoch logs, classification metrics, and a confusion matrix as concrete evidence.
- What you can do after
- Apply it via an LLM-generated Python notebook, then validate training behavior and select metrics and thresholds for the business risk.
WordPress Power Toolkit: Harness AI to build next-level websites
Deep learning is a machine-learning approach that uses multilayer artificial neural networks to learn hierarchical representations from large amounts of data.
- How it is used
- Applies layered learning to uncover hidden patterns in massive datasets, including website analytics and visitor behavior.
- How deep it goes
- Defines multilayer neural networks and hierarchical representations, but does not explain training mechanics or network internals.
- Examples
- Uses website analytics and AlphaGo Zero’s independently discovered Go strategies as concrete examples.
Read how WordPress Power Toolkit: Harness AI to build next-level websites explains deep learning →
Delivering Machine Learning Projects: From design to deployment
A deep neural network is a neural-network model composed of multiple computational layers that learn hierarchical representations from data.
- How it is used
- Deploys deep networks for complex unstructured data when simpler algorithms cannot adequately address the modeling problem.
- How deep it goes
- Explains architecture-specific inductive bias and operational trade-offs, but stops short of detailed training algorithms or mathematics.
- Examples
- Uses pixel-order limitations, convolutional localities, learned filters, and comparisons among five hierarchical network families.
- What you can do after
- Evaluate deep-network choices against data structure, benchmark performance, transparency, training cost, inference latency, and production expense.
Read how Delivering Machine Learning Projects: From design to deployment explains deep learning →
Data-Driven Cybersecurity
Deep learning is a machine-learning approach that uses neural networks with multiple learned layers to represent complex patterns.
- How it is used
- Detects cybersecurity threats by learning patterns in files, network activity, and user behavior.
- How deep it goes
- Defines layered neural networks and explains applications, then works through training and evaluation without detailing model internals.
- Examples
- Uses malware classification, suspicious network sequences, unusual file access, and a network-traffic threat-classification exercise.
- What you can do after
- Build from scratch: preprocess network data, train a TensorFlow/Keras neural network, and evaluate predictions with classification metrics.
Introduction to Generative AI, Second Edition
Deep learning is a machine-learning subfield based on neural networks with multiple hidden layers.
- How it is used
- Uses multilayer neural networks to model complex patterns, especially in natural language processing.
- How deep it goes
- Defines layers, nodes, weights, biases, objectives, and parameters, but defers the precise training mathematics.
- Examples
- Uses text-based natural language tasks and large language models as examples of neural-network applications.
- What you can do after
- Understand how layered neural networks learn representations for data-rich tasks and why parameter count signals model complexity.
Read how Introduction to Generative AI, Second Edition explains deep learning →
Applied Reinforcement Learning
Deep learning is a machine-learning approach that learns hierarchical representations and predictions using neural networks with multiple learned layers.
- How it is used
- Uses neural networks as expressive function approximators for high-dimensional states in deep Q-learning.
- How deep it goes
- Explains the forward pass, layer transformations, neuron computation, and activation role.
- Examples
- Names images, sensor vectors, medical records, and high-dimensional states as possible network inputs.
- What you can do after
- Understand how learned layers and nonlinear activations transform complex inputs into Q-value predictions.
Read how Applied Reinforcement Learning explains deep learning →
Machines that Think
Deep learning is a machine-learning approach that learns hierarchical representations through neural networks with multiple layers.
- How it is used
- Uses layered neural networks to learn features for tasks such as image recognition, speech processing, and language modeling.
- How deep it goes
- Explains hierarchical feature formation and depth-related benefits, while deferring training challenges to later discussion.
- Examples
- Uses image edges and shapes, sentence meaning, review sentiment, and email categorization as examples.
- What you can do after
- Understand how hidden layers build increasingly abstract features and why greater depth can help or complicate training.
Also covered in
- Fight Fraud with Machine LearningIn early access (MEAP)
- Distributed Machine Learning Patterns
- Build an Advanced RAG Application (From Scratch)In early access (MEAP)
- AI-Powered Developer: Build software with ChatGPT and Copilot
- Data Storytelling with Altair and AI
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.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- 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
- 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.
- 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.
- language modelincludes · A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- neural networkuses · A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
- GPT modelincludes · A GPT model is a generative, autoregressive Transformer language model in the family developed by OpenAI.
- 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.
Questions about deep learning
What is deep learning?
Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
Which Manning books explain deep learning?
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI, Inside AI, Grokking Machine Learning, Second Edition, Build AI Drug Discovery Pipelines, Data Without Labels, Outlier Detection in Python, Designing Deep Learning Systems: A guide for software engineers, Transfer Learning for Natural Language Processing and 12 more.
What should I know before learning deep learning?
Manning books that teach deep learning usually introduce machine learning, artificial intelligence, language model and objective function first.
What kinds of deep learning are there?
Kinds of deep learning include autoencoder, language model, GPT model and recurrent neural network.
What is deep learning a kind of?
Deep learning is a kind of machine learning. Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
What is deep learning also called?
Deep learning is also called DL.
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.



















