Book Image

Real-World Python Deep Learning Projects [Video]

By : Jakub Konczyk
Book Image

Real-World Python Deep Learning Projects [Video]

By: Jakub Konczyk

Overview of this book

<p>Deep Learning allows you to solve problems where traditional Machine Learning methods might perform poorly: detecting and extracting objects from images, extracting meaning from text, and predicting outcomes based on complex dependencies, to name a few. In this course you will learn how to use Deep Learning in practice by going through real-world examples.</p> <p>You will start of by creating neural networks to predict the demand for airline travel in the future. Then, you'll run through a scenario where you have to identify negative tweets for a celebrity by using Convolutional Neural Networks (CNN's). Next you will create a neural network which will be able to identify smiles in your camera app. Finally, the last project will help you forecast a company's stock prices for the next day using Deep Learning.</p> <p>By the end of this course, you will have a solid understanding of Deep Learning and the ability to build your own Deep Learning models.</p> <p>The code bundle for this video course is available at -&nbsp;<a href="https://github.com/PacktPublishing/Real-World-Python-Deep-Learning-Projects" target="_blank">https://github.com/PacktPublishing/Real-World-Python-Deep-Learning-Projects</a></p> <h1>Style and Approach</h1> <p>This course will teach you Deep Learning using easy-to-understand, practical, and clear examples. Each Deep Learning use case is based on a real-world dataset.</p>
Table of Contents (5 chapters)
Chapter 2
Predicting Demand for Airline Travel
Content Locked
Section 1
Based on Past Data, Predicting the Number of Airline Passengers
An overview of the process of solving a time series prediction problem using deep learning methods. - The first step is to phrase our problem in the correct way and prepare data for working with a neural network. - Then we need to build our neural network in Python. - The last step is to train our model with our data and tweak it for best performance. Then we can just use it make a prediction.