How deeply does Data Without Labels cover deep learning?

Explains network components and supervised training through loss and backpropagation, then introduces unlabeled training methods.

Deep learning

As explained in Data Without Labels

A deep learning model is a machine-learning model composed of multiple layers of learned representations.

Deep learning is machine learning based on neural networks. It is particularly useful for unstructured data such as images, text, audio, and video, where conventional machine-learning methods may be less effective. It can also be used with structured data. The goal is to learn patterns from data for tasks such as recognition, prediction, or grouping. section 8.1.1 section 8.13

A neural network learns through connected components and a training process:

Artificial neurons use weights and biases; input, hidden, and output layers organize the network. Hidden layers learn features used in decisions, while activation functions affect its outputs. section 8.13
With labeled data, training seeks useful weights and biases through feed-forward propagation, loss calculation, and backpropagation. section 8.13 section 8.3
With unlabeled data, a network can instead learn structure such as groupings or distributions. Unsupervised approaches include the Boltzmann learning rule and deep belief networks. section 8.5

Recognizing faces

To identify people in images, train a network on face images paired with names. It begins without knowing which image attributes identify a person and learns distinguishing characteristics from the labeled examples. An unlabeled image task would differ: it might group similar pictures without assigning supplied names. section 8.2.1 section 8.5

Architecture should fit the data: convolutional neural networks are used for image and video patterns, while recurrent neural networks handle sequences such as language and time series. Before choosing a complex model, check whether representative, good-quality data and enough training capacity are available. Deep learning is not a solution to every business problem. section 8.13 section 8.11

How Data Without Labels covers it

liveBook manning.com

Read Data Without Labels on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIA machine learning approach based on neural networks with multiple learned layers of representation.
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

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 Data Without Labels. The section links point to the parts of the book it draws on.