Deep learning

As explained in Inside AI

A deep neural network is a neural network containing multiple hidden layers that learn hierarchical representations from simpler features.

Deep learning helps computers find patterns in large, complex datasets. It is used for tasks such as recognizing images, processing speech and assessing fraud risk. Its results can be impressive, but success at a task should not be mistaken for human-like understanding. section 3.4.1 section 3.8

A deep neural network is a neural network with multiple hidden layers between its input and output. These layers can build representations of complex features from simpler patterns. During training, the network adjusts numerical weights to reduce errors; adding layers does not, by itself, make it more intelligent. section 3.4 section 3.8

Figure 3.4 A deep neural network architecture

The architecture diagram shows the layers that give a deep neural network its name. section 3.4

Recognizing a cat

An image-recognition network can learn to classify pictures as “cat” or “not cat” from many labeled examples showing different appearances and viewpoints. Unlike a child who can generalize from an early encounter, the network learns weights that support its predictions—not what a cat means or how one behaves. section 6.2

The practical choice depends on both the task and the available data:

• Consider deep learning for pattern-heavy tasks such as image recognition, language processing, diagnosis support and predictive analytics. section 3.4.1
• Check whether enough suitable labeled data is available. Training can take time, performance may suffer on data unlike the training set, and changing objectives can require expensive retraining. section 3.4.2
• Consider combining it with other methods when a problem also calls for historical cases, handling uncertainty or explainable rules, as in a proposed fraud-prevention system. section 11.7

How Inside AI covers it

How deep it goes

Explains hidden layers, hierarchical patterns and weight adjustment conceptually, while deferring detailed theory and implementation.

Examples

Uses cat-image classification and Siri’s spoken wake-phrase detection to illustrate visual and audio pattern recognition.

What it assumes

Introduces neural-network layers and weights without assuming detailed theory or mathematical formulas.

What you can do after

Evaluate/understand when deep learning suits a pattern-recognition task and when data needs, retraining costs or limited generalization constrain it.

How it connects

Connects neural networks and backpropagation to generative AI and combinations with data mining, fuzzy logic and rule-based systems.

liveBookmanning.com

Read Inside AI 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
  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
  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.
• 

  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 Inside AI. The section links point to the parts of the book it draws on.