Getting Started with Java Deep Learning
2.2 (3 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
27 students enrolled
Wishlisted Wishlist

Please confirm that you want to add Getting Started with Java Deep Learning to your Wishlist.

Add to Wishlist

Getting Started with Java Deep Learning

Get the essential know-how on working with deep learning algorithms using Java
2.2 (3 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
27 students enrolled
Created by Packt Publishing
Last updated 4/2017
English
Current price: $10 Original price: $125 Discount: 92% off
5 hours left at this price!
30-Day Money-Back Guarantee
Includes:
  • 2 hours on-demand video
  • 1 Supplemental Resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • Get a practical deep dive into deep learning algorithms
  • Implement well-known algorithms related to deep learning
  • Explore neural networks using some of the most popular deep learning frameworks
  • Dive into Deep Belief Nets and Stacked Denoising Autoencoders algorithms
  • Discover more Deep Learning algorithms with Convolutional Neural Networks
  • Get a practical insight about how to tune models.
View Curriculum
Requirements
  • Software requirement
  • Windows 10
  • IntelliJ IDEA
  • Gradle
  • Sdkman
  • deeplearning4j
Description

AI and deep learning are transforming the way we understand software, making computers more intelligent than we could even imagine just a decade ago. It is the technology behind self-driven cars, intelligent personal assistant computers, and decision support systems. Deep learning algorithms are being used across a broad range of industries. As the fundamental driver of AI, being able to tackle deep learning with Java is going to be a vital and valuable skill, not only within the tech world, but also for the wider global economy that depends upon knowledge and insight for growth and success.

You will learn how to install the environment, where Git is used as version control, Eclipse or IntelliJ as an IDE, and mostly Gradle with a little bit of Maven as a build tool. You will learn how to use the DL4J and apply deep learning to a range of real-world use cases. You will then be introduced to Neural networks and later you will learn how to implement them. You will also be given an insight about various deep learning algorithms. You will then be trained to tune Apache Spark.

By the end of the video course, you’ll be ready to tackle deep learning with Java. Wherever you’ve come from—whether you’re a data scientist or Java developer—you will become a part of the deep learning revolution!

About the Author

Sercan Karaoglu gained his BSc in Mathematics Engineering at Istanbul Technical University. Karaoglu also completed a Research and Development project at age 23, at Foreks, in collaboration with The Scientific and Technological Research Council of Turkey(TUBITAK). This project was related to the application of Artificial Neural Networks in Financial Trading Decision Support Systems and Market Simulation for Intraday and Daily Trading.

Currently, he develops High Throughput-Low Latency Reactive Microservices and Reactive Stream applications at work and researches the topics of Deep Learning and Machine Learning. He is Java Software Engineer at the Dissemination Department of Foreks Information Systems, which is one of the leading IT companies in Turkey’s financial sector. It has specialized in software that is directly integrated with financial professionals and Istanbul Stock Market for over 26 years.

He is currently studying for his MSc in Computer Engineering at Bahcesehir University in the field of Big Data Analytics and Management.

Who is the target audience?
  • Developers who are new to Data science & machine learning concepts.
  • Basic knowledge of software development and Java
  • People who want to get started with Enterprise level Deep Learning
  • Should be aware of calculus, to make the most out of this course
Students Who Viewed This Course Also Viewed
Curriculum For This Course
20 Lectures
01:54:05
+
Installation and Setup
4 Lectures 20:19

This video will provide you an overview of the entire course. 

Preview 05:14

The aim of this video is to set up your environment for the course. Therefore we are going to install necessary software such as JDK, Gradle, Git, and IntelliJ.

Installing on Windows
10:07

The aim of this video is to show how we can manage dependencies before creating the project, and take advantage of both GPU and CPU.

Quick Start
02:28

The aim of this video to show how to take advantage of GPUs for deep learning algorithms.

Building NN Using GPU
02:30
+
Neural Networks
4 Lectures 20:08

This video shows you what classification and clustering are and how they can be implemented in Java using industry standard framework deeplearning4j.

Preview 09:28

Learn one of the most important building block in Neural Networks, which is Activation Functions, in specific Softmax Function.

Softmax Function
02:33

This problem occurs when we need to build a model where there are continuous to continuous variables such as when we have a bunch of housing data, which includes room size location and its price tag, in this case, there is nothing to classify instead predicting the true price for the house based on its features.

Multilinear Regression
03:39

This video deals with binary classification problem such as identifying if something is right or wrong, 1 or 0, yes or no, and so on. It is a simple decision making process.

Logistic Regression
04:28
+
Implementing Neural Nets
4 Lectures 22:39

This video tells you about one of the most important building block neural networks, which is optimizers, in specific, Gradient Descent. Because Neural Networks are not just black boxes and one cannot just take and use it without understanding the underlying concept it is very important for you to watch and understand fundamental concepts.

Preview 05:08

Up to now, we talked about some linear models. These are the simplest models and works okay for most cases. However, sometimes there is a nonlinear relationship between features and the target values. In this section, we are going to introduce how we solve when nonlinear relationship is seen in the data.

Multilayer Perceptron
07:25

This video explains the first and simplest type of neural net that is used for a lot of classification task. It is an abstraction for both the single layer perceptron and multilayer perceptron.

Feed-Forward Neural Networks
04:16

Recurrent Neural Networks are solution for predicting the flowing data like time series, sound, natural language, movie frame etc.

Recurrent Neural Networks
05:50
+
Deeper Architectures
4 Lectures 35:20

Recurrent Neural Networks are good at sequence modelling; however, sometimes they tend to remember only recent events and forget about the past events. So, in this case, we are going to use Long Short Term Memory (LSTM).

Preview 03:50

Convolutional Neural Networks are useful where we want to train a network to recognize patterns that aren't tied to specific location in the image. This also allows us to save a lot of parameters compared to the fully connected layer and helps to reduce over fitting.

Convolutional Neural Networks
06:50

This video introduces a neural network that is used for dimension reduction, feature selection, and feature extraction.

Denoising Autoencoders
13:13

The aim of this video is to introduce you to one of the popular deep learning algorithms that is used in the recommender systems.

Restricted Boltzmann Machine
11:27
+
Tuning
4 Lectures 15:39

Neural networks have something called as the hyper-parameter space, which means they have a lot of parameters to tune, which affect the model dramatically. Therefore in this video the goal is to give you some tips and tricks about parameter tuning.

Preview 04:04

Neural networks have something called hyper parameter space which means they have a lot of parameters to tune which affect the model dramatically. Therefore, in this video the goal is to give you some tips and tricks about parameter tuning.

Fixing and Selecting Parameters
04:41

Understand regularization method called early stopping that prevents neural network from over training.

Early Stopping
03:54

The aim of this video is to show how to test and evaluate models and how to do that using deeplearning4j.

Testing and Evaluating
03:00
About the Instructor
Packt Publishing
3.9 Average rating
7,264 Reviews
51,786 Students
616 Courses
Tech Knowledge in Motion

Packt has been committed to developer learning since 2004. A lot has changed in software since then - but Packt has remained responsive to these changes, continuing to look forward at the trends and tools defining the way we work and live. And how to put them to work.

With an extensive library of content - more than 4000 books and video courses -Packt's mission is to help developers stay relevant in a rapidly changing world. From new web frameworks and programming languages, to cutting edge data analytics, and DevOps, Packt takes software professionals in every field to what's important to them now.

From skills that will help you to develop and future proof your career to immediate solutions to every day tech challenges, Packt is a go-to resource to make you a better, smarter developer.

Packt Udemy courses continue this tradition, bringing you comprehensive yet concise video courses straight from the experts.