Feathering a python interface for artificial neural networks with its straightforward approach and focus on user experience, Keras is empowering the developers with ease of learning and model building, offering a single API that works across several Machine learning frameworks.

Being one of the leading high-level neural network APIs, Keras that is defined for human beings and not machines is written in python and supports multiple backends neural network computation engines like Tensorflow, CNTK, Theano, MXNet, and PlaidML. A very powerful and easy-to-use free open source python library, Keras develops and evaluates deep learning models by wrapping around the functionalities of other ML and DL libraries like Theano and Tensorflow defining and training neural network models in just a few lines of code. Following the best practices of reducing cognitive load, Keras allows the users to productize deep models on smartphones, allows the usage of distributed training of deep learning models on clusters of GPU and TPU, and acts as an interface for the Tensorflow library making it easier to navigate.

Expressive, flexible, and apt for innovative research, and backed by Google, Microsoft, Amazon, Apple, Nvidia, Uber, and others, Is Keras capable to handle low-level computations?

- MADHAVI DESAI