Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Complete Artificial Neural Networks & Deep Learning In R
INTRODUCTION TO THE COURSE: The Key Concepts and Software Tools
Introduction (1:31)
Data and Scripts For the Course
Install R and RStudio (6:36)
Read CSV and Excel Data (9:56)
Read in Online CSV (4:04)
Read in Data from Online HTML Tables-Part 1 (4:13)
Read in Data from Online HTML Tables-Part 2 (6:24)
Remove NAs (17:12)
More Data Cleaning (8:05)
Introduction to dplyr for Data Summarizing-Part 1 (6:11)
Introduction to dplyr for Data Summarizing-Part 2 (4:44)
Exploratory Data Analysis(EDA): Basic Visualizations with R (18:53)
More Exploratory Data Analysis with xda (4:16)
Difference Between Supervised & Unsupervised Learning (5:32)
Introduction to Artificial Neural Networks (ANN)
Theory Behind ANN (Artificial Neural Network) and DNN (Deep Neural Networks) (9:17)
Neural Network for Binary Classifications (6:51)
Neural Network with PCA for Binary Classifications (3:57)
Evaluate Accuracy (4:19)
Multi Layer Perceptron (MLP) (4:45)
Neural Network for Multiclass Classifications (7:04)
Neural Network for Image Type Data (4:31)
Multi-class Classification Using Neural Networks with caret (8:26)
Neural Network for Regression (4:31)
More on Neural Networks- with neuralnet (4:31)
Identify Variable Importance in Neural Networks (8:49)
Start With Deep Neural Network (DNN)
Implement a Simple DNN With "neuralnet" for Binary Classifications (8:09)
Implement a Simple DNN With "deepnet" for Regression (4:15)
A Package for DNN Modelling in R-H2o (5:37)
Working with External Data in H2o (4:21)
Implement an ANN with H2o For Multi-Class Supervised Classification (10:30)
Implement a DNN with H2o For Multi-Class Supervised Classification (6:17)
Implement a (Less Intensive) DNN with H2o For Supervised Classification (3:58)
Identify Variable Importance (9:02)
What Are Activation Functions? (5:50)
Implement a DNN with H2o For Regression (3:51)
Autoencoders for Unsupervised Learning (1:46)
Autoencoders for Credit Card Fraud Detection (4:11)
Use the Autoencoder Model for Anomaly Detection (5:00)
Autoencoders for Unsupervised Classification (6:57)
ANN & DNN With MXNet Package in R
Install MXnet in R and RStudio (3:13)
Install MxNet in R
Implement an ANN Based Classification Using MXNet (8:29)
Implement an ANN Based Regression Using MXNet (3:48)
Implement a DNN Based Multi-Class Classification With MXNet (10:46)
Evaluate Accuracy of the DNN Model (2:47)
Implement MXNET via "caret" (6:16)
Convolution Neural Networks (CNN)
What is a CNN? (11:25)
Implement a CNN for Multi-Class Supervised Classification (8:31)
More About Our CNN Model Accuracy (5:52)
Implement CNN on Actual Images with MxNet (7:44)
RNNs With Temporal Data (7:42)
Neural Network for Binary Classifications
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock