Anomaly Detection Using Deep Learning and Autoencoders

Deep Learning Project- Learn about implementation of a machine learning algorithm using autoencoders for anomaly detection.

Videos

Each project comes with 2-5 hours of micro-videos explaining the solution.

Code & Dataset

Get access to 50+ solved projects with iPython notebooks and datasets.

Project Experience

Add project experience to your Linkedin/Github profiles.

What will you learn

  • Understanding the problem statement

  • Importing the dataset and importing libraries

  • Performing basic EDA and checking for null values

  • Imputing the null values filling them using appropriate method

  • Using ggplot to visualize the Dataset

  • Importing h2o library and initializing an h2o cluster

  • Splitting Dataset into Train and Test

  • Defining parameters for training a Neural Network

  • Training the neural network for making predictions

  • Understanding what is difference between Artificial Neural Networks and Autoencoders

  • How does an Autoencoder work

  • Loading the pre-trained Neural Network

  • How to Autoencode a pre-trained Neural Networks

  • Visualizing the effectiveness of an Autoencoded model and a Neural Networks using ggplot

  • Making predictions using the trained model

Project Description

Deep learning is an upcoming field, where we are seeing a lot of implementations in day-to-day business operations, including segmentation, clustering, forecasting, prediction or recommendation etc. Deep learning architecture has many branches and one of them is the deep neural network (DNN), the method that we are going to analyze in this deep learning project is about the role of Autoencoders in performing classification and optimizing the hyperparameters.

Similar Projects

Big Data Project Solving Multiple Classification use cases Using H2O
In this project, we are going to talk about H2O and functionality in terms of building Machine Learning models.
Big Data Project Predict Census Income using Deep Learning Models
In this project, we are going to work on Deep Learning using H2O to predict Census income.

Curriculum For This Mini Project

 
  Problem Statement
03m
  Read CSV File
01m
  What is Deep Learning
05m
  First Steps
01m
  Univariate & Bivariate examples
04m
  Correlation between variables
07m
  Logistic Regression to predict Anomaly
05m
  Compute ROC curve from Logistic Regression Model
05m
  Train, test and validation of the model
03m
  Deep Learning Models to predict Anomaly
02m
  Rattle
10m
  Problems with Traditional Neural Networks
04m
  Deep Learning Libraries in R
06m
  MXNet Library
16m
  H2O Library
14m
  Data Exploratory Stage
10m
  Initialize the Model
03m
  Create Data Partition
04m
  Apply AutoEncoders
07m
  Analyse Model Result
08m
  Saving and Loading Model
03m
  Generate Predictions
10m
  Generate Model with 3 layers
16m
  Features Dimension
20m
  Cross Train the model
09m
  Anomaly Detection
23m