Book Image

TensorFlow Developer Certificate Guide

By : Oluwole Fagbohun
4 (2)
Book Image

TensorFlow Developer Certificate Guide

4 (2)
By: Oluwole Fagbohun

Overview of this book

The TensorFlow Developer Certificate Guide is an indispensable resource for machine learning enthusiasts and data professionals seeking to master TensorFlow and validate their skills by earning the certification. This practical guide equips you with the skills and knowledge necessary to build robust deep learning models that effectively tackle real-world challenges across diverse industries. You’ll embark on a journey of skill acquisition through easy-to-follow, step-by-step explanations and practical examples, mastering the craft of building sophisticated models using TensorFlow 2.x and overcoming common hurdles such as overfitting and data augmentation. With this book, you’ll discover a wide range of practical applications, including computer vision, natural language processing, and time series prediction. To prepare you for the TensorFlow Developer Certificate exam, it offers comprehensive coverage of exam topics, including image classification, natural language processing (NLP), and time series analysis. With the TensorFlow certification, you’ll be primed to tackle a broad spectrum of business problems and advance your career in the exciting field of machine learning. Whether you are a novice or an experienced developer, this guide will propel you to achieve your aspirations and become a highly skilled TensorFlow professional.
Table of Contents (20 chapters)
1
Part 1 – Introduction to TensorFlow
6
Part 2 – Image Classification with TensorFlow
12
Part 3 – Natural Language Processing with TensorFlow
15
Part 4 – Time Series with TensorFlow

Challenges of image recognition with fully connected networks

In Chapter 5, Image Classification with Neural Networks, we applied a deep neural network (DNN) to the Fashion MNIST dataset. We saw how every neuron in the input layer is connected to every neuron in the hidden layer and those in the hidden layer are connected to neurons in the output layer, hence the name fully connected. While this architecture can solve many ML problems, they are not well suited for modeling image classification tasks, due to the spatial nature of image data. Let’s say you are looking at a picture of a face; the positioning and orientation of the features on the face enable you to know it is a human face even when you just focus on a specific feature, such as the eyes. Instinctively, you know it’s a face by virtue of the spatial relationship between the features of the face; however, DNNs do not see this bigger picture when looking at images. They process each pixel in the image as independent...