Keras

As explained in Grokking Machine Learning

An open-source deep-learning library providing high-level APIs for constructing and training neural networks.

Keras is a high-level API for building and training neural networks. A sequential model is assembled from layers, then compiled and fit to data. Examples include classifying points in a circular, nonlinear pattern and recognizing handwritten digits. section 10.3

A typical workflow in these examples is to:

• Preprocess inputs and convert class labels to categorical vectors. section 10.3
• Add dense layers and dropout, then compile with a loss, optimizer, and accuracy metric. section 10.3
• Train with fit and use predictions to classify test images. section 10.3

Figure 10.20 Neural networks are great for nonlinearly separable sets. To test this, we’ll train a neural network on this circular dataset.

The circular dataset illustrates why a neural network can be useful when classes require a nonlinear decision boundary. section 10.3

How Grokking Machine Learning covers it

How deep it goes

Demonstrates preprocessing, layer construction, compilation, training, and prediction without detailing library internals.

Examples

Uses a two-feature circular dataset and MNIST handwritten digits to demonstrate classification.

What it assumes

Assumes neural-network theory, while demonstrating data preprocessing and model training in practice.

What you can do after

Build from scratch and train classifiers for nonlinear points and handwritten digits.

How it connects

Connects Keras with neural networks, TensorFlow, and PyTorch.

liveBookmanning.com

Read Grokking Machine Learning on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Deep Learning with R, Third EditionKeras is an open-source deep learning API for building and training neural networks.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIKeras is an open-source deep learning API for Python that provides interfaces for building and training neural-network models.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionThe programming interface of Keras that exposes multiple model-construction workflows and lets them interoperate.
• 

  liveBookmanning.com
  Distributed Machine Learning PatternsKeras is a high-level deep-learning API for defining, training, evaluating, and exporting neural-network models, commonly used through TensorFlow as tf.keras.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksKeras is an open-source deep-learning library providing high-level APIs for constructing and training neural networks.

Compare how 6 books explain Keras →

Related concepts

• TensorFlowuses · TensorFlow is an open-source software platform for numerical computation and machine learning, with tools for developing, training, and deploying models.
• autoencoderused by · An autoencoder is a neural network that encodes input data into an internal representation and decodes it to reconstruct the input or an approximation.
• deep learninguses · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
• PyTorchuses · PyTorch is an open-source machine-learning framework for Python that provides tensor computation, automatic differentiation, and tools for building and training neural networks.
• backenduses · A backend is a software component or subsystem that provides underlying processing, data access, execution, or services to clients or other components, typically behind a user-facing interface.
• backpropagationimplements · Backpropagation is a procedure for computing derivatives of an output or loss with respect to inputs and parameters by applying the chain rule backward through a computational graph.

This explainer was generated by Manning's knowledge graph from the text of Grokking Machine Learning. The section links point to the parts of the book it draws on.