Sign In Start Free Trial

Neural Network Projects with Python

By : James Loy

4.6 (15)

Neural Network Projects with Python

4.6 (15)

By: James Loy

Overview of this book

Neural networks are at the core of recent AI advances, providing some of the best resolutions to many real-world problems, including image recognition, medical diagnosis, text analysis, and more. This book goes through some basic neural network and deep learning concepts, as well as some popular libraries in Python for implementing them. It contains practical demonstrations of neural networks in domains such as fare prediction, image classification, sentiment analysis, and more. In each case, the book provides a problem statement, the specific neural network architecture required to tackle that problem, the reasoning behind the algorithm used, and the associated Python code to implement the solution from scratch. In the process, you will gain hands-on experience with using popular Python libraries such as Keras to build and train your own neural networks from scratch. By the end of this book, you will have mastered the different neural network architectures and created cutting-edge AI projects in Python that will immediately strengthen your machine learning portfolio.

Preface

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Machine Learning and Neural Networks 101

Machine Learning and Neural Networks 101

What is machine learning?

Setting up your computer for machine learning

Neural networks

pandas – a powerful data analysis toolkit in Python

TensorFlow and Keras – open source deep learning libraries

Other Python libraries

Summary

Predicting Diabetes with Multilayer Perceptrons

Predicting Diabetes with Multilayer Perceptrons

Technical requirements

Diabetes – understanding the problem

AI in healthcare

The diabetes mellitus dataset

Exploratory data analysis

Data preprocessing

MLPs

Model building in Python using Keras

Results analysis

Summary

Questions

Predicting Taxi Fares with Deep Feedforward Networks

Predicting Taxi Fares with Deep Feedforward Networks

Technical requirements

Predicting taxi fares in New York City

The NYC taxi fares dataset

Exploratory data analysis

Data preprocessing

Feature engineering

Feature scaling

Deep feedforward networks

Model building in Python using Keras

Results analysis

Putting it all together

Summary

Questions

Cats Versus Dogs - Image Classification Using CNNs

Cats Versus Dogs - Image Classification Using CNNs

Technical requirements

Computer vision and object recognition

Types of object recognition tasks

Digital images as neural network input

Building blocks of CNNs

Basic architecture of CNNs

A review of modern CNNs

The cats and dogs dataset

Managing image data for Keras

Image augmentation

Model building

Results analysis

Summary

Questions

Removing Noise from Images Using Autoencoders

Removing Noise from Images Using Autoencoders

Technical requirements

What are autoencoders?

Latent representation

Autoencoders for data compression

The MNIST handwritten digits dataset

Building a simple autoencoder

Denoising autoencoders

Denoising documents with autoencoders

Summary

Questions

Sentiment Analysis of Movie Reviews Using LSTM

Sentiment Analysis of Movie Reviews Using LSTM

Technical requirements

Sequential problems in machine learning

NLP and sentiment analysis

RNN

The LSTM network

The IMDb movie reviews dataset

Representing words as vectors

Model architecture

Model building in Keras

Analyzing the results

Putting it all together

Summary

Questions

Implementing a Facial Recognition System with Neural Networks

Implementing a Facial Recognition System with Neural Networks

Technical requirements

Facial recognition systems

Breaking down the face recognition problem

Requirements of face recognition systems

One-shot learning

Siamese neural networks

Contrastive loss

The faces dataset

Creating a Siamese neural network in Keras

Model training in Keras

Analyzing the results

Consolidating our code

Creating a real-time face recognition program

Summary

Questions

What's Next?

What's Next?

Putting it all together

Cutting edge advancements in neural networks

Limitations of neural networks

The future of artificial intelligence and machine learning

Keeping up with machine learning

Favorite machine learning tools

Summary

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

4.6 (15)

5 star

80%

4 star

6.7%

3 star

6.7%

2 star

6.7%

1 star

0

Questions

How is face detection different than face recognition?

The objective of face detection is to locate human faces in an image. The output from the face detection process is a bounding box around detected faces. On the other hand, the objective of face recognition is to classify faces (that is, identify subjects). Face detection and face recognition are the two key steps in every facial recognition system, and the output from the face detection step is passed as input to the face recognition step.

What is the Viola-Jones algorithm for face detection?

The Viola-Jones algorithm uses Haar features for face detection. Haar features are filters with alternating dark and bright areas that represents the contrast in pixel intensity in human faces. For example, the eye area in an image of a human face has a darker pixel value than the forehead and the cheeks areas. These...

Search

Your notes and bookmarks