Python Libraries Keras example

 Keras: High-Level Neural Networks API

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, Theano, or CNTK. It focuses on enabling fast experimentation and is known for its user-friendliness. It's designed to make building and training neural networks as easy as possible.

Key Features & Why it's Useful:

• User-Friendly API: Keras provides a simple and intuitive API that makes it easy to define and train neural network models, even for beginners.
• Modularity: Neural networks are built by connecting modular layers (e.g., dense layers, convolutional layers, recurrent layers). Keras makes it easy to combine these layers to create complex architectures.
• Extensibility: You can easily create custom layers, loss functions, and metrics to tailor Keras to your specific needs.
• Multiple Backends: Keras can run on top of different backends (TensorFlow, Theano, CNTK), giving you flexibility in terms of performance and hardware support. However, TensorFlow is now the primary and recommended backend.
• Built-in Datasets & Preprocessing: Keras provides access to several built-in datasets (e.g., MNIST, CIFAR-10) and tools for data preprocessing.
• Focus on Rapid Prototyping: Keras is designed for fast experimentation. You can quickly build and test different model architectures.

Simple Example:

import keras
from keras.models import Sequential
from keras.layers import Dense

# Define the model
model = Sequential()
model.add(Dense(128, activation='relu', input_shape=(784,)))  # Input layer with 784 features
model.add(Dense(10, activation='softmax'))  # Output layer with 10 classes

# Compile the model
model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

# Load and preprocess data (example using MNIST)
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = x_train.reshape(60000, 784).astype('float32') / 255
x_test = x_test.reshape(10000, 784).astype('float32') / 255
y_train = keras.utils.to_categorical(y_train, num_classes=10)
y_test = keras.utils.to_categorical(y_test, num_classes=10)

# Train the model
model.fit(x_train, y_train, epochs=2)

# Evaluate the model
loss, accuracy = model.evaluate(x_test, y_test)
print('Test accuracy:', accuracy)