Getting started: Installing Numpy, Keras and TensorFlow Keras is a high-level Python API that allows you to easily construct, train, and apply neural networks. However, Keras is not a neural network library itself and depends on one of several neural network backends. We will use the Tensorflow backend. TensorFlow is an open-source library for neural networks (and other mathematical models based on sequences of matrix and tensor computations), originally developed by Google.Also, Keras uses numpy data structures. Installing Numpy, TensorFlow and Keras We suggest that you use the Python package management system pip. On most systems, the following commands will work: pip install numpy matplotlib. $ pip install tensorflow pip install keras OR Using Anaconda (Easy and Prefered) $conda install keras scikit-learn pandas Note that this will likely install the CPU version of TensorFlow that does not use the GPU to speed up neural network training. For this assignment, training on the CPU will be sufficient, but if your computer has a GPU (or you want to try running the assignment in the cloud), follow the installation instructions on the tensorflow page If you get stuck during the installation, you can find installation instructions for each package here: Tensorflow: https://www.tensorflow.org/install/ . Keras: https://keras.io/#installation Introduction In this assignment you will use the Keras Neural Network API for Python to build neural networks for image classification