R: Artificial Neural Nets in R - Beginner to Expert!: 3-in-1
3.5 (1 rating)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
15 students enrolled

R: Artificial Neural Nets in R - Beginner to Expert!: 3-in-1

Implement solutions from scratch, covering real-world case studies to illustrate the power of neural network models.
3.5 (1 rating)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
15 students enrolled
Created by Packt Publishing
Last updated 8/2018
English
English [Auto-generated]
Current price: $139.99 Original price: $199.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 5.5 hours on-demand video
  • 1 downloadable resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Implement supervised and unsupervised machine learning in R for neural networks.
  • Predict and classify data automatically using neural networks.
  • Align your data science strategy with current and future systems in their respective ecosystem.
  • Visualize leakages in your organization and fix them with deep learning.
  • Predict outcomes of processes and propose improvements.
  • Explore the Perceptron classifier
  • Stack with a neural network
  • Evaluate and fine-tune the models you build.
  • Work with neurons, perceptron, bias, weights, and activation functions
  • Gain a practical understanding of the architectures required to develop business use cases
Course content
Expand all 50 lectures 05:32:03
+ Getting Started with Neural Nets in R
16 lectures 02:25:01

This video will give you an overview about the course. 

Preview 01:51

The aim of this video is to study the basics of Neural Networks.                         

  • What are Neural Nets?

  • How Neurons function?

Introduction to Neural Nets
08:06

The aim of this video is to study Neural Net Components.                         

  • Study about Perceptron Elements

  • Get to know about Combination function

  • What is an Output function?

Neural Nets Components
10:09

The aim of this video is to study about Matrices and Neural Nets.                         

  • How do Matrices work in neural networks?

  • Get to know about Matrices- Operations

  • Get to know about Matrices-Multiplication

Matrices and Neural Nets
07:05

The aim of this video is to study Forward and Backward Propagation.                         

  • What are FeedForward Neural Nets?

  • Get to know about Delta Rule - BackPropagation

Forward and Backward Propagation
19:25

The aim of this video is to study about MNIST practically.                         

  • What is MNIST Dataset?

  • Get to know about Softmax Regression Example

  • Demo

MNIST Example
20:51

The aim of this video is to study Neural Nets from Scratch?                         

  • Why from Scratch?

  • Understand the leaky abstractions behind neural networks

Preview 05:47

The aim of this video is to study the Regression and Softmax Conepts.                         

  • Get to know about Linear Regression as Neural Net

  • Study about Multinomial Logistic Regression

  • Get to explore CNN

Regression and Softmax Concepts
09:13

The aim of this video is to study about NN Demo.                         

  • What are Neural Network function?

  • Demo

NN Demo
09:37

The aim of this video is to study customer Churn data.                         

  • What are the different R packages for Training?

  • Discuss Overfitting and Underfitting

  • Get to know what is Regularization

Customer Churn Data
10:46

The aim of this video is to work on Neural Nets using Keras and packages in R.                         

  • Study the different libraries.

  • Learn the key things in artificial neural networks

  • Call the function called bake()

Neural Nets Demo
08:08

The aim of this video is to learn how to build a 3 layer MLP with multi-class predictors with Keras.                         

  • Learn about sequential model

  • How to do Overfitting?

Build a 3 Layer MLP with Keras
08:29

The aim of this video is to learn how to visualize neural networks with LIME.                         

  • Set up the classification model

  • Study the heat map.

  • Study LIME Cases

Visualize Neural Networks
08:43

The aim of this video is to study the movie review data.                         

  • Take a look at Sample Movie Review Data

  • What is Dataset Encoding?

Movie Review Data
04:05

The aim of this video is to study RNN.                         

  • What is RNN?

  • Get to know about and Unrolled RNN

  • Study about LSTM.

RNN
05:04

The aim of this video is to study about RNN/LSTM with a Demo.                         

  • How to build a LSTM Layer?

  • Plot the Training and Validation

  • Get a look at Predictions

RNN/LSTM Demo
07:42
Test your knowledge
4 questions
+ Create Your Own Sophisticated Model with Neural Networks
17 lectures 01:24:49

This video will give you an overview about the course.   

Preview 03:06

In this video we will perform some basic classification with decision trees and then visualize a decision tree with pydot.                         

  • Import libraries

  • Measure the accuracy on the test set

  • Visualize the content

Decision Trees – Classification and Visualization
04:41

We will continue to explore the iris dataset further by focusing  on the first two features (sepal length and sepal width), optimizing the  decision tree, and creating some visualizations.                         

  • View the data with pandas

  • Select the best performing tree with the best_estimator_ attribute

  • Visualize the tree with graphviz

Tuning a Decision Tree
05:18

Decision trees for regression are very similar to decision trees  for classification. The procedure for developing a regression model  consists of four parts: First Load the dataset, then split the set into  training/testing subsets, after that instantiate a decision tree  regressor and train it, and finally score the model on the test subset.                         

  • Create a decision tree regressor, instantiate the decision tree and train it

  • Measure the model's accuracy

  • Use an error metric to compare y_test (ground truth) and y_pred (model predictions)

Using Decision Trees for Regression
03:48

Here, we will use cross-validation on the diabetes dataset to improve performance.                         

  • Use grid search to reduce overfitting

  • Check the error metrics

  •   Check the mean percentage error

Reducing Overfitting with Cross-Validation
02:55

Ensemble algorithms use several algorithms together to improve  predictions. A random forest is a mixture of several decision trees,  where each tree provides a single vote toward the final prediction. The  final random forest calculates a final output by averaging the results  of all the trees it is composed of.                         

  • Import and instantiate a random forest

  • Measure prediction error

  • Use the estimators_attribute

Implementing Random Forest Regression
03:22

It does not necessarily involve trees. It builds several instances  of a base estimator acting on random subsets of the first training set.  Bagging estimators are great for reducing the variance of a complex  base estimator.                         

  • Import BaggingRegressor and KNeighborsRegressor

  • Instantiate the KNeighboursRegressor class and pass it as the base_estimator within BaggingRegressor

  • Look at the best parameters in the random search run

Bagging Regression with Nearest Neighbors
04:11

Here we will Focus on important parameters in the gradient  boosting algorithm, Create a parameter distribution where the most  important parameters are varied, Perform a random grid search and Use  the best parameters from the previous step with many estimators.                         

  • Load the gradient boosting algorithm and random grid search

  • Create a parameter distribution for the gradient boosting trees

  • Run the grid search to find the best parameters

Tuning Gradient Boosting Trees and AdaBoost Regressor
08:09

The fundamental process in the stacking aggregator is that we use  the predictions of several machine learning algorithms as input for the  training of another machine learning algorithm.                         

  • Using RandomizedSearchCV, find the best parameters

  • Train the best parameter set with more estimators

  • Predict the target using X_stack using both algorithms

Defining a Stacking Aggregator with scikit-learn
06:50

LDA attempts to fit a linear combination of features to predict an  outcome variable. LDA is often used as a pre-processing step. We'll  walk through both methods in this video.                         

  • Stock data from Google

  • Flatten out the dataset

  • Fit the LDA object

Using LDA for Classification
05:17

QDA is the generalization of a common technique such as quadratic  regression. It is simply a generalization of a model to allow for more  complex models to fit. SGD is a fundamental technique used to fit a  model for regression. There are natural connections between SGD for  classification or regression.                         

  • Learn a nonlinear LDA

  • Use SGD for classification

Using QDA and SGD for Classification
03:39

Naive Bayes is a really interesting model. It's somewhat similar  to KNN in the sense that it makes some assumptions that might  oversimplify reality, but still it performs well in many cases.                         

  • Pre-process the data into a bag-of-words matrix

  • Fire up the classifier and fit our model

  • Rename the sets bow and newgroups.target to X and y respectively

Classifying Documents with Naive Bayes
04:57

Label propagation is a semi-supervised technique that makes use of  labeled and unlabeled data to learn about unlabeled data. Quite often,  data that will benefit from a classification algorithm is difficult to  label.                         

  • Update y with -1

  • Use the LabelPropagation method to predict the labels

  • Measure the accuracy score

Label Propagation with Semi-Supervised Learning
03:54

With scikit-learn, you can explore the perceptron classifier and  relate it to other classification procedures within scikit-learn.                         

  • Load the UCI diabetes classification dataset

  • Split the dataset into training and test sets

  • Import and instantiate  a perceptron

Perceptron Classifier
05:10

Here first we will load the data, then scale the data with a  standard scaler, after that do a hyperparameter search and finally vary  the alpha parameter.                         

  • Scale the data with a standard scaler

  • Perform the scaling on the test set

  • Perform a randomized search 

Multilayer Perceptron
02:33

The two most common meta-learning methods are bagging and  boosting. Stacking is less widely used; yet it is powerful because one  can combine models of different types.                         

  • Split the dataset into training and testing sets

  • Split the training set into two sets

  • Train base learners on the first part of the training set

Stacking with a Neural Network
10:08

Here we are going to do some work towards building our own  scikit-learn estimator. The custom scikit-learn estimator consists of at  least three methods: Init initialization method, fit method and predict  method.                         

  • Load the breast cancer dataset from scikit learn

  • Split the data into training and testing sets

  • Import BaseEstimator and ClassifierMixin from sklearn.base and pass them along as arguments to your new classifier

Creating a Simple Estimator
06:51
+ Deep Learning Architecture for Building Artificial Neural Networks
17 lectures 01:42:13

This video gives an overview of the entire course. 

Preview 04:24

In this video, we will go through an overview of Deep Learning.                         

  • Go through an overview of Deep Learning

  • Understand the concept of Deep Learning

Deep Learning Overview
09:51

In this video, we will understand what Deep Learning is.                         

  • Learn about Deep Learning in real world.

  • Understand the practical applications of Deep Learning

Deep Learning in the Real World
09:05

In this video, we will explore the environments of Deep Learning.                         

  • Study the environments of Deep learning

  • Learn how to set up Deep learning

Environments of Deep Learning
04:25

In this video, we will learn how to get started with Deep learning.                         

  • Go through the prerequisites

  • Explore the Don’t in Deep learning

  • Understand Deep learning

Getting Started with Deep Learning
05:24

In this video, we will understand the working of neural Networks.                         

  • Learn how neural networks works

  • Learn what does a neural network contains

  • Understand the uses of neural network

How Do Neural Networks Work?
07:12

In this video, we will explore more on Neural networks.                         

  • Understand how neural networks learn

  • Learn how does it work in practice

  • Learn how to start an initiative in neural network

How Do Neural Networks Learn?
06:46

In this video, we will learn about the Deep learning Architectures.                         

  • Go through the major architectures of deep learning

  • Understand the advance deep learning architectures

Neural Networks for Deep Learning Architecture
07:16

In this video, we will learn about supervised, unsupervised and semi supervised learning.                         

  • Understand the concept of supervised learning

  • Understand the concept of unsupervised learning

  • Understand the concept of semi supervised learning

Supervised Versus Unsupervised Learning
04:12

In this video, we will understand the various components of deep learning.                         

  • Explore the components of deep learning

  • Go through the architectural configurations

Components of Deep Learning Architecture
04:03

In this video, we will learn about setting up Deep architectures.                         

  • Learn how to set up

  • Go through some use cases

  • Derive the output

Set Up Deep Architectures and Align with Outputs
04:46

In this video, we will see how to Set up Datasets for Deep Learning with Sample Datasets.                         

  • Learn how and where to get data sets

  • Go through some samples

Set up Datasets for Deep Learning with Sample Datasets
04:14

In this video, we will go through the steps to build the Deep learning platforms.                         

  • Go through the steps to build deep learning platform

  • Explore the key opportunities

Steps to Build Deep Learning Platforms
06:06

This video will show you what artificial neural network is.                         

  • Learn what is ANN

  • Learn about Artificial Neural model

  • Go through the applications of ANN

What Is an Artificial Neural Network?
06:38

In this video, we will learn how to build artificial neural network.                         

  • Learn how to build ANN-prerequisites

  • Learn how to design a network

  • Learn how to train a network

How to Build Artificial Neural Network – Prerequisites
06:11

This video will show you the Business problems through ANN.                         

  • Define a business problem

  • Go through a real life business problem

Business Problems Through ANN
05:48

This video will show you the solutions through ANN.                         

  • Define a business problem

  • Solution it through ANN

Solutions Through ANN
05:52
Test your knowledge
4 questions
Requirements
  • Basic understanding of Python and R (statistical background plus a basic knowledge) would be useful to anyone taking this course.
  • A sound knowledge of Anaconda (and its libraries such as NumPy and scikit-learn) is required.
Description

Neural networks are one of the most fascinating machine learning models for solving complex computational problems efficiently. Neural networks are used to solve a wide range of problems in different areas of AI and machine learning. The advantage of neural network is that it is adaptive in nature. It learns from the information provided, i.e. trains itself from the data, which has a known outcome and optimizes its weights for a better prediction in situations with unknown outcome.

R provides this machine learning environment under a strong programming platform, which not only provides the supporting computation paradigm but also offers enormous flexibility on related data processing. The open source version of R and the supporting neural network packages are very easy to install and also simple to learn. Machine learning is widely used in many areas, ranging from the diagnosis of diseases to weather forecasting. You can also experiment with any novel example, which you feel can be interesting to solve using a neural network.

This comprehensive 3-in-1 course is a step-by-step guide to understanding Neural Networks with R; throughout the course, practical, real-world examples help you get acquainted with the various concepts of Neural Networks. Develop a strong background in neural networks with R, to implement them in your applications. Learn how to build and train neural network models to solve complex problems. Implement solutions from scratch, covering real-world case studies to illustrate the power of neural network models.

Contents and Overview

This training program includes 3 complete courses, carefully chosen to give you the most comprehensive training possible.

The first course, Getting Started with Neural Nets in R, covers building and training neural network models to solve complex problems. This course explains the niche aspects of neural networking and provides you with a foundation from which to get started with advanced topics by implementing them in R. This course covers an introduction to neural nets, the R language, and building neural nets from scratch- with R packages; specific worked models are applied to practical problems such as image recognition, pattern recognition, and recommender systems. At the end of the course, you will learn to implement neural network models in your applications with the help of practical examples from companies using neural nets.

The second course, Create Your Own Sophisticated Model with Neural Networks, covers one-stop solution to learning complex models with Neural Networks and understanding the basics of Natural Language Processing. With this course you will learn the Decision Tree algorithms and Ensemble Models to build Random Forest, Regression Analysis. Focus on Decision Trees and Ensemble Algorithms. Use scikit-learn to classify text and Multiclass with scikit-learn. Explore various algorithms for classification. Look at Naive Bayes model and Label Propagation. Finally, you'll use Neural Networks using different Classifiers and create your own Simple Estimator.

The third course, Deep Learning Architecture for Building Artificial Neural Networks, covers an introduction to deep learning and its architectures with real-world use cases. The course starts off with an introduction to Deep Learning and the different tools, hardware, and software before we begin to understand the different training models. We then get to what everyone is talking about: Neural Networks. Understand how Neural Networks work and the benefits they offer for supervised and well as unsupervised learning before building our very own neural network. Explore the different Deep Learning Architectures, including how to set up your architecture and align the output. Finally we take a look at Artificial Neural Networks and understand how to build your own ANN.

Taking this course will help you dive head first into the popular field of deep learning as a career choice or for further learning.

By the end of the course, you’ll develop a strong background in neural networks with R, to build and train neural network models and solve complex problems.

About the Authors

●        ArunKrishnaswamyhas over 18 years of experience with large datasets, statistical methods, machine learning and software systems. He is one of the First Hadoop Engineers in the world, Advisor to AI Startups. He has 15+ years’ experience using R. He is also a Ph.D. in Statistics/Math with MS in CS. Expertise in Machine Learning, Neural Nets, and Deep Learning. Deep Experience in AWS, Spark, Cassandra, MongoDB, SQL, NoSQL, Tableau, R, Visualization. Data Science Mentor at UC Berkeley, Stanford, Caltech.Guest Lecturer at Community Colleges. Data Science in different domains o Fintech (Lending Club), o Cybersecurity (VISA) o Advertising Technology (Yahoo / Microsoft) o Bot Technology (voicy .ai) o Retail (WRS) o IOT (GE) o ERP (SAP) o Health Care (Blue Cross).

●        Julian Avila is a programmer and data scientist in finance and computer vision. He graduated from the Massachusetts Institute of Technology (MIT) in mathematics, where he researched quantum mechanical computation, a field involving physics, math, and computer science. While at MIT, Julian first picked up classical and flamenco guitars, Machine Learning, and artificial intelligence through discussions with friends in the CSAIL lab. He started programming in middle school, including games and geometrically artistic animations. He competed successfully in math and programming and worked for several groups at MIT. Julian has written complete software projects in elegant Python with just-in-time compilation. Some memorable projects of his include a large-scale facial recognition system for videos with neural networks on GPUs, recognizing parts of neurons within pictures, and stock-market trading programs.

●        Anshul is a global technology leader who has been instrumental in driving technology transformations for business revenues in the range of multi Billion USD. His experience has been in taking up strategic technology initiatives, architecting, delivering, and managing them at an enterprise level. Anshul has several notable career accomplishments, wherein he has led, created, and launched key ecommerce, mobile, and business intelligence initiatives for the world's #1 insurance brand AXA, in the fastest growing emerging markets of Asia. He is currently in a leadership role as the Chief Information Officer Information Technology and Digital Officer, leading the IT Strategy, Technology Transformations, Analytics, software delivery, architecture and Cloud for Union Insurance (UAE, Oman and Bahrain) across all lines of business (Life, General (P&C ) and Health Insurance) Creating and Driving big strategic Initiatives aligning IT transformation to deliver business value. Major Cloud transformations impacted the bottom line of Union by multimillion AED in the first year. Transformation on Digital added multimillion revenues in Life, P&C and Health lines of business. Machine Learning, Deep Learning and Robotic Process Automation are some key business transformations implemented recently. He is a transformational leader and Senior Management IT professional, with almost two decades of experience spread across multiple geographies (US, Europe, Southeast Asia, and the Middle East). Anshul has built and led local, regional, and global teams across 3 continents, and capitalized on opportunities to drive revenues, profits, and growth. Strong P&L management. Anshul has been mentoring startups, management students (IIM Bangalore), and incubators/accelerators such as Astrolabs Dubai, T Labs, CH9, Flat 6 labs, and other incubators since 2012. Startups mentored are in the tech space of analytics, mobility, tech-based microfinance institutions, healthcare tech and analytics, and tech-based retail merchandising, logistics and mobile wallets spread across geographies including Singapore, Dubai and Middle East, India and Europe. Anshul is a speaker on Blockchain, Internet of Things (IoT), Artificial Intelligence, Machine and Deep Learning, Digital Transformation, Cloud and Mobility. He won a couple of Star Performer of the Year Awards from AXA India & AXA Asia. Three times he has been awarded the AXA innovation award both at AXA Asia and AXA Group level.

-CIO of the year award, InfoSec Maestro Award, CSO Next of the year award.

-CISO award from MESA Dubai.

-CIO award from CNME Dubai.

Anshul writes on innovation, big data and technology transformations, Blockchain and had a couple of articles published in CNME, Innovation and Tech Middle East, Dataquest, LinkedIn, and PM Network.

Who this course is for:
  • Anyone who wants to work with neural networks to understand real-world examples. If you are interested in artificial intelligence and deep learning and you want to level up, then this course is what you need!
  • Programmers, analysts, architects, data scientists, or anyone working in a big data environments and interested in learning how to implement Artificial intelligence in the world of Data Science. Taking this course will help you to take a first step in designing your career as a deep learning architect.