Book Image

Deep Learning with TensorFlow

By : Giancarlo Zaccone, Md. Rezaul Karim, Ahmed Menshawy
Book Image

Deep Learning with TensorFlow

By: Giancarlo Zaccone, Md. Rezaul Karim, Ahmed Menshawy

Overview of this book

Deep learning is the step that comes after machine learning, and has more advanced implementations. Machine learning is not just for academics anymore, but is becoming a mainstream practice through wide adoption, and deep learning has taken the front seat. As a data scientist, if you want to explore data abstraction layers, this book will be your guide. This book shows how this can be exploited in the real world with complex raw data using TensorFlow 1.x. Throughout the book, you’ll learn how to implement deep learning algorithms for machine learning systems and integrate them into your product offerings, including search, image recognition, and language processing. Additionally, you’ll learn how to analyze and improve the performance of deep learning models. This can be done by comparing algorithms against benchmarks, along with machine intelligence, to learn from the information and determine ideal behaviors within a specific context. After finishing the book, you will be familiar with machine learning techniques, in particular the use of TensorFlow for deep learning, and will be ready to apply your knowledge to research or commercial projects.
Table of Contents (11 chapters)

ReLU classifier

The last architectural change improved the accuracy of our model, but we can do even better by changing the sigmoid activation function with the Rectified Linear Unit, shown as follows:

ReLU function

A Rectified Linear Unit (ReLU) unit computes the function f(x) = max(0, x), ReLU is computationally fast because it does not require any exponential computation, such as those required in sigmoid or tanh activations, furthermore it was found to greatly accelerate the convergence of stochastic gradient descent compared to the sigmoid/tanh functions.

To use the ReLU function, we simply change, in the previously implemented model, the following definitions of the first four layers, in the previously implemented model.

First layer output:

Y1 = tf.nn.relu(tf.matmul(XX, W1) + B1)  

Second layer output:

Y2 = tf.nn.relu(tf.matmul(Y1, W2) + B2) 

Third layer output:

Y3 = tf.nn.relu(tf.matmul(Y2, W3) + B3) ...