Book Image

Deep Learning with Keras

By : Antonio Gulli, Sujit Pal
Book Image

Deep Learning with Keras

By: Antonio Gulli, Sujit Pal

Overview of this book

This book starts by introducing you to supervised learning algorithms such as simple linear regression, the classical multilayer perceptron and more sophisticated deep convolutional networks. You will also explore image processing with recognition of handwritten digit images, classification of images into different categories, and advanced objects recognition with related image annotations. An example of identification of salient points for face detection is also provided. Next you will be introduced to Recurrent Networks, which are optimized for processing sequence data such as text, audio or time series. Following that, you will learn about unsupervised learning algorithms such as Autoencoders and the very popular Generative Adversarial Networks (GANs). You will also explore non-traditional uses of neural networks as Style Transfer. Finally, you will look at reinforcement learning and its application to AI game playing, another popular direction of research and application of neural networks.
Table of Contents (16 chapters)
Title Page
Credits
About the Authors
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface

Perceptron


The perceptron is a simple algorithm which, given an input vector x of m values (x1, x2, ..., xn) often called input features or simply features, outputs either 1 (yes) or 0 (no). Mathematically, we define a function:

Here, w is a vector of weights, wx is the dot product

, and b is a bias. If you remember elementary geometry, wx + b defines a boundary hyperplane that changes position according to the values assigned to w and b. If x lies above the straight line, then the answer is positive, otherwise it is negative. Very simple algorithm! The perception cannot express a maybe answer. It can answer yes (1) or no (0) if we understand how to define w and b, that is the training process that will be discussed in the following paragraphs.

The first example of Keras code

The initial building block of Keras is a model, and the simplest model is called sequential. A sequential Keras model is a linear pipeline (a stack) of neural networks layers. This code fragment defines a single layer with 12 artificial neurons, and it expects 8 input variables (also known as features):

from keras.models import Sequential
model = Sequential()
model.add(Dense(12, input_dim=8, kernel_initializer='random_uniform'))

Each neuron can be initialized with specific weights. Keras provides a few choices, the most common of which are listed as follows:

  • random_uniform: Weights are initialized to uniformly random small values in (-0.05, 0.05). In other words, any value within the given interval is equally likely to be drawn.
  • random_normal: Weights are initialized according to a Gaussian, with a zero mean and small standard deviation of 0.05. For those of you who are not familiar with a Gaussian, think about a symmetric bell curve shape.
  • zero: All weights are initialized to zero.

A full list is available at https://keras.io/initializations/.