4.33 out of 5
4.33
120 reviews on Udemy

Practical Neural Networks & Deep Learning In R

Artificial Intelligence & Machine Learning for Practical Data Science in R
Instructor:
Minerva Singh
810 students enrolled
English [Auto-generated]
Be Able To Harness The Power Of R For Practical Data Science
Read In Data Into The R Environment From Different Sources & Carry Out Basic Pre-processing Tasks
Master The Theory Of Artificial Neural Networks (ANN)
Implement ANN For Classification & Regression Problems In R
Implement Deep Learning In R
Learn The Usage Of The Powerful H2o Package
Learn The Implementation Of Both ANN & DNN Using The H2o Package Of R Programming Language

YOUR COMPLETE GUIDE TO PRACTICAL NEURAL NETWORKS & DEEP LEARNING IN R:       

This course covers the main aspects of neural networks and deep learning. If you take this course, you can do away with taking other courses or buying books on R based data science.

 In this age of big data, companies across the globe use R to sift through the avalanche of information at their disposal. By becoming proficient in neural networks and deep learning in R, you can give your company a competitive edge and boost your career to the next level!

LEARN FROM AN EXPERT DATA SCIENTIST:

My name is Minerva Singh and I am an Oxford University MPhil (Geography and Environment) graduate. I recently finished a PhD at Cambridge University.

I have +5 years of experience in analyzing real life data from different sources using data science related techniques and producing publications for international peer reviewed journals.

Over the course of my research I realized almost all the R data science courses and books out there do not account for the multidimensional nature of the topic .

This course will give you a robust grounding in the main aspects of practical neural networks and deep learning. 

Unlike other R instructors, I dig deep into the data science features of R and give you a one-of-a-kind grounding in data science…

You will go all the way from carrying out data reading & cleaning  to to finally implementing powerful neural networks and deep learning algorithms and evaluating their performance using R.

Among other things:

  • You will be introduced to powerful R-based deep learning packages such as h2o and MXNET.

  • You will be introduced to deep neural networks (DNN), convolution neural networks (CNN) and recurrent neural networks (RNN).

  • You will learn to apply these frameworks to real life data including credit card fraud data, tumor data, images among others for classification and regression applications.  

With this course, you’ll have the keys to the entire R Neural Networks and Deep Learning Kingdom!

NO PRIOR R OR STATISTICS/MACHINE LEARNING KNOWLEDGE IS REQUIRED:

You’ll start by absorbing the most valuable R Data Science basics and techniques. I use easy-to-understand, hands-on methods to simplify and address even the most difficult concepts in R.

My course will help you implement the methods using real data obtained from different sources. Many courses use made-up data that does not empower students to implement R based data science in real-life.

After taking this course, you’ll easily use data science packages like caret, h2o, mxnet to work with real data in R…

You’ll even understand the underlying concepts to understand what algorithms and methods are best suited for your data.

We will also work with real data and you will have access to all the code and data used in the course. 

JOIN MY COURSE NOW!

INTRODUCTION TO THE COURSE: The Key Concepts and Software Tools

1
Introduction
2
Data and Scripts For the Course
3
Installing R and R Studio
4
Read in CSV & Excel Data
5
Read in Online CSV
6
Read in Data from Online HTML Tables-Part 1
7
Read in Data from Online HTML Tables-Part 2
8
Remove Missing Values
9
More Data Cleaning
10
Introduction to dplyr for Data Summarizing-Part 1
11
Introduction to dplyr for Data Summarizing-Part 2
12
Exploratory Data Analysis(EDA): Basic Visualizations with R
13
More Exploratory Data Analysis with xda
14
Difference Between Supervised & Unsupervised Learning

Introduction to Artificial Neural Networks (ANN)

1
Theory Behind ANN (Artificial Neural Network) and DNN (Deep Neural Networks)
2
Neural Network for Binary Classifications
3
Neural Network with PCA for Binary Classifications
4
Evaluate Accuracy
5
Implement a Multi-Layer Perceptron (MLP) For Supervised Classification
6
Neural Network for Multiclass Classifications
7
Neural Network for Image Type Data
8
Multi-class Classification Using Neural Networks with caret
9
Neural Network for Regression
10
More on Neural Networks- with neuralnet
11
Identify Variable Importance in Neural Networks

Start With Deep Neural Network (DNN)

1
Implement a Simple DNN With "neuralnet" for Binary Classifications
2
Implement a Simple DNN With "deepnet" for Regression
3
A Package for DNN Modelling in R-H2o
4
Working with External Data in H2o
5
Implement an ANN with H2o For Multi-Class Supervised Classification
6
Implement a DNN with H2o For Multi-Class Supervised Classification
7
Implement a (Less Intensive) DNN with H2o For Supervised Classification
8
Identify Variable Importance
9
What Are Activation Functions?
10
Implement a DNN with H2o For Regression
11
Autoencoders for Unsupervised Learning
12
Autoencoders for Credit Card Fraud Detection
13
Use the Autoencoder Model for Anomaly Detection
14
Autoencoders for Unsupervised Classification

ANN & DNN With MXNet Package in R

1
Install MXnet in R and RStudio
2
MXNEt Installation Code For R
3
Implement an ANN Based Classification Using MXNet
4
Implement an ANN Based Regression Using MXNet
5
Implement a DNN Based Multi-Class Classification With MXNet
6
Evaluate Accuracy of the DNN Model
7
Implement MXNET via "caret"

Convolution Neural Networks (CNN)

1
What is a CNN?
2
Implement a CNN for Multi-Class Supervised Classification
3
More About Our CNN Model Accuracy
4
Implement CNN on Actual Images with MxNet
5
RNNs With Temporal Data
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.3
4.3 out of 5
120 Ratings

Detailed Rating

Stars 5
73
Stars 4
21
Stars 3
18
Stars 2
4
Stars 1
4
e3f9f6fa170f8c86283211296389152e
30-Day Money-Back Guarantee

Includes

5 hours on-demand video
2 articles
Full lifetime access
Access on mobile and TV
Certificate of Completion