Deep learning

As explained in 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.

Deep learning is used to create models for problems such as recognizing a customer’s intent and matching a question to a relevant answer. Model development explores training data, selects training algorithms, trains models, and develops inference code for unseen data. A production deep learning system extends that work: it connects the model lifecycle to the people, pipelines, services, and product requirements needed to use models reliably at scale. section 1.1.3 section 1.3 section 1.0

A practical path from idea to deployed model includes:

• Translate a product need into a prediction task and measurable serving requirements, including prediction rate and latency. section 1.1.3
• Explore available data, prototype training code, compare experimental models, and select an appropriate model. section 1.1.3 section 10.1
• Stabilize and package training code, inference code, and source models so system services can train, track, and serve them. section 10.4
• Design serving around model inputs and outputs, training-framework environments, user scenarios, latency, and resource efficiency. section 6.1.4

Intent-based customer support

A support application can replace a confusing navigation menu with natural-language questions. Teams prototype candidate models using training data, evaluate them, then productionize the selected model with continuous data processing, training, deployment, evaluation, and model serving. The application backend calls the serving service while the service meets specified throughput and latency needs. section 1.1.3

Research and prototyping are interactive: practitioners explore data, write and revise training code, train and test experimental models, compare metrics, and track versions of data and code. Once a training workflow and inference response are satisfactory, product integration can begin. Deployment strategy becomes important when inference service cannot be interrupted, and deployment approaches can also support production experimentation. section 10.1.1 section 10.4

Figure 10.3 Excerpt of the path to production in the research and prototyping phases

Use the production-path diagram to place research and iterative prototyping before packaging and broader productionization work. section 10.1

How Designing Deep Learning Systems: A guide for software engineers covers it

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.

How it connects

Links training data, training algorithms, inference code, model serving, deployment strategy, dataset management, and hyperparameter optimization.

liveBookmanning.com

Read Designing Deep Learning Systems: A guide for software engineers 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
  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 Designing Deep Learning Systems: A guide for software engineers. The section links point to the parts of the book it draws on.