Skip to content
Last Dictionary
Plane
AI Engineering & MLOpsDeep Learning
trademark

Keras

proper nounAlso: tf.keras, Keras 3, Keras Core

In plain wordsA free, beginner-friendly Python library for building neural networks from ready-made layers in a few lines of code, while a larger toolkit underneath does the heavy computing.

  1. A high-level Python library for defining and training neural networks in very little code, trading low-level control for brevity and readability. Models are assembled from layer objects in one of three styles — the Sequential API for linear stacks, the functional API for graphs of layers with multiple inputs and outputs, and subclassing for full control — then configured with compile (choosing optimizer, lossloss function, n.: A score that measures how wrong a model's predictions are. Training means adjusting the model, step by step, to push this number down. and metrics), trained with fit, assessed with evaluate and applied with predict. Keras delegates tensor computation to a backend: at first TheanoTheano, prop. n.: One of the first popular free software tools for deep learning, built at a Montreal university lab; development ended in 2017, but it shaped the toolkits that replaced it., soon also TensorFlowTensorFlow, prop. n.: Google's free software toolkit for building, training and running machine-learning models; it led the field after 2015 and still runs many models inside phones, browsers and company systems. and, from 2017, Microsoft's CNTK. TensorFlow bundled it as tf.keras from 2017; after multi-backend Keras was discontinued in 2019–2020 it was TensorFlow-only until Keras 3 (2023) added JAXJAX, prop. n.: A free Google library that lets researchers write mathematics in familiar Python and automatically get derivatives and very fast code for graphics chips and Google's AI chips. and PyTorchPyTorch, prop. n.: The most widely used free software toolkit for building and training neural networks, especially in research; programmers write ordinary Python and it handles the calculus and the graphics chips. backends, so the same model code can run on different frameworks. Companion libraries such as KerasHub provide pretrained models. Its compile-and-fit pattern influenced many later high-level libraries.

    For the class project, a dozen lines of Keras produced a working image classifier.

Origin

Created by François Chollet and released in March 2015, initially running on Theano. The name is the Greek word for horn, alluding to the gate of horn in the Odyssey through which truthful dreams pass. Google, where Chollet worked, made it TensorFlow's official high-level API, and Keras 3 restored multi-backend support in November 2023.

Related

See also
  • TensorFlowTensorFlow, prop. n.: Google's free software toolkit for building, training and running machine-learning models; it led the field after 2015 and still runs many models inside phones, browsers and company systems.
  • PyTorchPyTorch, prop. n.: The most widely used free software toolkit for building and training neural networks, especially in research; programmers write ordinary Python and it handles the calculus and the graphics chips.
  • JAXJAX, prop. n.: A free Google library that lets researchers write mathematics in familiar Python and automatically get derivatives and very fast code for graphics chips and Google's AI chips.
  • TheanoTheano, prop. n.: One of the first popular free software tools for deep learning, built at a Montreal university lab; development ended in 2017, but it shaped the toolkits that replaced it.
  • deep learningdeep learning, n.: Machine learning done with neural networks built from many stacked layers: raw data such as pixels, sound or text goes in at one end, and each layer turns what it receives into something more abstract.
  • scikit-learnscikit-learn, prop. n.: A free, widely taught Python library of classic machine-learning methods — such as decision trees, regression and clustering — that all work in the same simple way.

Mentioned in

TensorFlowTensorFlow, prop. n.: Google's free software toolkit for building, training and running machine-learning models; it led the field after 2015 and still runs many models inside phones, browsers and company systems., François CholletFrançois Chollet, prop. n.: A French software engineer who created Keras, a popular tool for building neural networks, and the ARC benchmark, which tests whether AI can solve kinds of puzzles it has never seen., JAXJAX, prop. n.: A free Google library that lets researchers write mathematics in familiar Python and automatically get derivatives and very fast code for graphics chips and Google's AI chips., TheanoTheano, prop. n.: One of the first popular free software tools for deep learning, built at a Montreal university lab; development ended in 2017, but it shaped the toolkits that replaced it.