Deep learning

Q: How deeply does Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI cover deep learning?

Explains preprocessing, Keras model definition, callback-controlled training, and evaluation while deferring detailed research surveys and neural-network internals.

As explained in Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI

A machine learning approach based on neural networks with multiple learned layers of representation.

Deep learning uses neural networks to map inputs to predictions through learned nonlinear transformations. Unlike classical machine learning, it can learn transformations end to end rather than relying entirely on manually engineered features. section 1.3 section 1.4

It is especially successful with images, audio, video, and text, but tabular business data presents a less settled choice. Gradient boosting is often the practical baseline because it can be simpler, more transparent, and strong on typical heterogeneous tables. section 1.4 section 1.6 section 5.2.3

Use deep learning for tabular prediction as a deliberate workflow:

Compare it with a classical baseline such as XGBoost using simplicity, transparency, and efficacy—not accuracy alone. section 3.0 section 3.5
Clean and reshape columns before training: handle missing values, convert numeric strings, and split mixed-purpose fields into usable features. section 9.6
Define preprocessing and model components with Keras layers, keeping hyperparameters in configuration where practical. section 9.3 section 9.4
Train with validation and callbacks such as early stopping, then evaluate on a test dataset and exercise the trained model on realistic cases. section 9.4 section 9.6

Classifying Kuala Lumpur property prices

A property dataset combines location, price, rooms, bathrooms, parking, property type, size, and furnishing. After cleaning its mixed and missing values, a Keras model predicts whether a listing price is above or below the market median; callbacks stop training when validation performance no longer improves. section 9.0 section 9.1 section 9.4

Deep learning can need substantial data to generalize well. With smaller tabular datasets, many columns, and higher overfitting risk, classical approaches may perform better; combining deep learning and gradient boosting can sometimes improve predictions because their errors differ. section 12.1 section 12.6

Table 12.1 Airbnb NYC problem vs Airbnb Tokyo problem (view table figure)

	Airbnb NYC	Airbnb Tokyo
Rows in dataset	48,000	10,000
Columns in dataset	18	31
Target	Classification: predict whether the price is over or under the median price	Regression: predict price

Compare the NYC classification and Tokyo regression datasets to see how row count, column count, and target type change the difficulty of applying deep learning. section 12.1

How Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI covers it

Cover of Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI

liveBook manning.com

Read Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Inside AIA deep neural network is a neural network containing multiple hidden layers that learn hierarchical representations from simpler features.
liveBook manning.com

Data Without LabelsA deep learning model is a machine-learning model composed of multiple layers of learned representations.
liveBook manning.com

Outlier Detection in PythonDeep learning is machine learning based on neural networks with multiple computational layers that learn hierarchical representations.
liveBook manning.com

Designing Deep Learning Systems: A guide for software engineersA machine learning model that uses multiple layers of learned representations to make predictions or decisions.
liveBook manning.com

Evolutionary Deep Learning: Genetic algorithms and neural networksA deep learning model is a neural network with multiple learned layers that learns hierarchical representations from data.
liveBook manning.com

Effective Data AnalysisDeep learning is a machine-learning approach that uses multilayered neural networks to learn representations and patterns from data.
liveBook manning.com

WordPress Power Toolkit: Harness AI to build next-level websitesDeep learning is a machine-learning approach that uses multilayer artificial neural networks to learn hierarchical representations from large amounts of data.
liveBook manning.com

Delivering Machine Learning Projects: From design to deploymentA deep neural network is a neural-network model composed of multiple computational layers that learn hierarchical representations from data.
liveBook manning.com

Data-Driven CybersecurityDeep learning is a machine-learning approach that uses neural networks with multiple learned layers to represent complex patterns.
liveBook manning.com

Introduction to Generative AI, Second EditionDeep learning is a machine-learning subfield based on neural networks with multiple hidden layers.

Compare how 11 books explain deep learning →

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.
language modelincludes · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
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.
neural networkuses · A neural network is a computational model of interconnected, parameterized units that learns transformations from inputs to outputs.
GPT modelincludes · A GPT model is a generative pretrained Transformer language model that produces text autoregressively by predicting successive tokens from preceding context.
recurrent neural networkincludes · A recurrent neural network is a neural network that processes sequences by updating an internal state across successive inputs, allowing earlier inputs to influence later computations.

This explainer was generated by Manning's knowledge graph from the text of Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI. The section links point to the parts of the book it draws on.