Deep learning

As explained in 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.

Deep learning uses multi-layer neural-network architectures to learn hierarchical representations, especially when inputs are complex and unstructured, such as images, sound, or natural language. section 7.3.3 section 7.3.4

Treat deep learning as a model-selection decision with explicit delivery checks:

• Benchmark a familiar algorithm before adopting a novel deep architecture; retain the simpler option when it meets the required output. section 7.3.3
• Match the architecture’s inductive bias to the data: convolutional networks capture image localities, while recurrent, graph, and attention-based networks target other structures. section 7.3.4
• Check transparency, training expense, inference latency, production cost, and environmental impact before treating functional performance as sufficient. section 7.3.3

Why architecture matters for images

A basic perceptron receives image pixels in sequence and loses their spatial relationships, making object recognition difficult. A convolutional network instead propagates information locally with learned sliding-window filters. section 7.3.4

Figure 7.6 Inductive bias in ML algorithms (adapted from Jumper, Evans, et. al. [6]. The sequence (a) through (e) is determined by the order in which these biases gained popularity in the ML community. The arrows indicate the propagation of signal across a network or in a graph.

Compare the inductive biases of multi-layer perceptrons, grid-based vision networks, recurrent networks, graph networks, and attention-based transformers. section 7.3.4

How Delivering Machine Learning Projects: From design to deployment covers it

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.

How it connects

Connects deep learning to inductive bias, convolutional networks, recurrent networks, graph networks, transformers, explainability, and model benchmarking.

liveBookmanning.com

Read Delivering Machine Learning Projects: From design to deployment on liveBook Get the book at manning.com

Also explained in

• 

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

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

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

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

  liveBookmanning.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.
• 

  liveBookmanning.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.
• 

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

  liveBookmanning.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.
• 

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

  liveBookmanning.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 Delivering Machine Learning Projects: From design to deployment. The section links point to the parts of the book it draws on.