Deep learning

As explained in Evolutionary Deep Learning: Genetic algorithms and neural networks

A deep learning model is a neural network with multiple learned layers that learns hierarchical representations from data.

Deep learning uses neural networks with multiple learned layers to solve AI and machine-learning tasks. Its practical challenge is not only training a network, but also developing, tuning, and optimizing a system that needs substantial data and computational resources. section 1.0 section 1.6

A usable model is rarely taken directly out of the box. Improvement can require choosing an architecture and adjusting options such as learning rate, activation function, training-data amount, batch size, epochs, and middle-layer size. These choices interact: larger models may fit better but take longer to train, while data and batch-size changes must be balanced. section 1.3 section 5.1.1

Evolutionary deep learning treats optimization as a broader automation problem across the development workflow:

• Use evolutionary computation to alter or create combined evolutionary computation/deep-learning models. section 1.5
• Apply approaches including neuroevolution, evolutionary hyperparameter optimization, and neuroevolution of augmenting topologies. section 1.6
• Contrast customizable evolutionary strategies with AutoML services, which can automate workflows but may limit agile customization. section 1.6

Tune a function-approximating network

Run a PyTorch notebook that approximates a function, then change middle-layer size, batch_size, and data_step. Compare predicted fit and training time; changing the middle layer to 25 or larger produces a better-fitting second test in the demonstrated run. section 5.1 section 5.1.1

Classify handwritten digits

Load and normalize MNIST images, train a network, inspect loss, accuracy, and a classification report, then run genetic-algorithm evolution and compare its accuracy progression with the trained model. section 6.5

Figure 1.4 Applying EC (EDL) to the AI/ML model development workflow for DL

Maps where evolutionary-computation methods can be applied to deep-learning development across the AI/ML workflow. section 1.5

How Evolutionary Deep Learning: Genetic algorithms and neural networks covers it

How deep it goes

Works through hyperparameter experiments and MNIST training, while deferring basic deep-learning principles to prior knowledge.

Examples

Uses PyTorch function approximation and TensorFlow/Keras MNIST handwritten-digit classification with evolutionary optimization.

What it assumes

Assumes perceptrons, multilayer perceptrons, activation functions, and optimization methods before hyperparameter tuning.

What you can do after

Apply it via PyTorch or Keras to train models, vary hyperparameters, and inspect fit, accuracy, and classification reports.

How it connects

Connects deep learning to evolutionary computation, AutoML, hyperparameter optimization, neural networks, and genetic algorithms.

liveBookmanning.com

Read Evolutionary Deep Learning: Genetic algorithms and neural networks 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
  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 Evolutionary Deep Learning: Genetic algorithms and neural networks. The section links point to the parts of the book it draws on.