Artificial Intelligence - Keras

Back to Course

Lesson Description

Lession - #854 Keras-Introduction

Profound learning is one of the major subfield of machine learning system. machine learning is the investigation of design of algorithm, motivated from the model of human brain. deep learning is turning out to be more well known in data science fields like robotics, artificial intelligence(AI>
, sound and video acknowledgment and picture acknowledgment. Artificial neural network is the center of deep learning approaches. deep learning is upheld by different libraries like Theano, TensorFlow, Caffe, Mxnet and so on, Keras is one of the most remarkable and simple to utilize python library, which is based on top of famous deep learning libraries like TensorFlow, Theano, and so forth, for making deep learning models.latest version keras is 2.4.0.keras means Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow.

Overview of Keras

Keras runs on top of open source machine libraries like TensorFlow, Theano or Cognitive Toolkit (CNTK>
. Theano is a python library utilized for quick mathematical calculation tasks. TensorFlow is the most popular symbolic math library utilized for making neural network and deep learning models. TensorFlow is entirely flexible and the essential advantage is circulated processing. CNTK is deep learning structure created by Microsoft. It utilizes libraries like Python, C#, C++ or independent machine learning toolboxs. Theano and TensorFlow are exceptionally strong libraries however hard to comprehend for making neural networks.

Keras depends on minimal structure that gives a spotless and simple method for making deep learning models in light of TensorFlow or Theano. Keras is intended to define deep learning models rapidly. Indeed, Keras is an ideal decision for deep learning applications.


Keras use different optimization techniques to make significant level neural network API simpler and more performant. It upholds the accompanying features −
  • Predictable, simple and extensible API.
  • Minimal design - simple to accomplish the results with no frills.
  • It supports various platforms and backends.
  • It is easy to use system which runs on both CPU and GPU.
  • Highly versatility of calculation.


    Following are the Benefits of Keras -
  • arger community support.
  • Simple to test.
  • Keras neural networks are written in Python which simplifies everything.
  • Keras upholds both convolution and recurrent networks.
  • deep learning models are discrete parts, so that, you can consolidate into numerous ways.
    Keras ImageDataGenerator is a pearl! It allows you to increase your pictures progressively while your model is as yet preparing.

    Keras Applications are deeplearning.<>/br keras vs tensorflow TensorFlow is an open-sourced end-to-end platform, a library for multiple machine learning tasks, while Keras is a high-level neural network library that runs on top of TensorFlow.
    keras-ocr provides out-of-the-box OCR models and an end-to-end training pipeline to build new OCR models.