Anomaly Detection with AutoEncoder using Tensorflow Keras

preview_player
Показать описание
Autoencoder is an unsupervised neural network model that uses reconstruction error to detect anomalies or outliers. The reconstruction error is the difference between the reconstructed data and the input data.

Autoencoder uses only normal data to train the model and all data to make predictions. Therefore, we expect outliers to have higher reconstruction errors because they are different from the regular data.

In this tutorial, we will use the Python Tensorflow Keras library to illustrate the process of identifying outliers using an autoencoder. To be specific, we will cover:

👉 What is the algorithm behind autoencoder for anomaly detection?
👉 How to train an autoencoder model?
👉 How to set a threshold for autoencoder anomaly detection?
👉 How to evaluate autoencoder anomaly detection performance?

⏰ Timecodes ⏰
0:00 - Intro
0:58 - Step 1: Import Libraries
1:27 - Step 2: Create Imbalanced Dataset
1:48 - Step 3: Train Test Split
2:27 - Step 4: Autoencoder Algorithm For Anomaly Detection
3:30 - Step 5: Autoencoder Model Training
5:43 - Step 6: Autoencoder Anomaly Detection Threshold
6:32 - Step 7: Autoencoder Anomaly Detection Performance
7:04 - Summary

❤️ Blog post with code for this video:

You will get full access to posts on Medium for $5 per month, and I will receive a portion of it. Thank you for your support!

🔥 Check out more machine learning tutorials on my website!

#anomalydetection #machinelearning #datascience #grabngoinfo
  1. Grab N Go Info
  2. Grab N Go Info
  3. machine learning
  4. data science
  5. deep learning
  6. python
Рекомендации по теме
What are Autoencoders? 0:05:00

What are Autoencoders?

Anomaly Detection with 0:08:15

Anomaly Detection with AutoEncoder using Tensorflow Keras

Anomaly Detection with 0:32:33

Anomaly Detection with AutoEncoders using Tensorflow

180 - LSTM 0:26:53

180 - LSTM Autoencoder for anomaly detection

Complete Deep Learning 0:23:06

Complete Deep Learning Project On Anomaly Detection with LSTM Autoencoder | Tensorflow Keras

Simple Explanation of 0:10:31

Simple Explanation of AutoEncoders

Anomaly Detection using 0:27:33

Anomaly Detection using Autoencoders

260 - Identifying 0:33:29

260 - Identifying anomaly images using convolutional autoencoders

Anomaly detection in 0:07:18

Anomaly detection in high energy physics using a quantum autoencoder

Complete Anomaly Detection 0:36:59

Complete Anomaly Detection Tutorials Machine Learning And Its Types With Implementation | Krish Naik

Anomaly Detection with 0:18:54

Anomaly Detection with Deep Learning Autoencoder By David Katz - January 2019

Autoencoders with Anomaly 0:21:26

Autoencoders with Anomaly Detection with CODE!

Anomaly Detection With 0:05:06

Anomaly Detection With Autoencoders

Introduction to Anomaly 0:14:57

Introduction to Anomaly Detection for Engineers

Anomaly detection with 0:45:29

Anomaly detection with TensorFlow | Workshop

Autoencoder Explained - 0:10:00

Autoencoder Explained - Deep Neural Networks

Using ML autoencoders 0:44:31

Using ML autoencoders for anomaly detection in accelerator controls

Anomaly detection in 0:23:00

Anomaly detection in driving scenario images with autoencoders

Anomaly Detection - 0:03:03

Anomaly Detection - Isolation Forest, AutoEncoders

Autoencoders and their 0:24:09

Autoencoders and their Potential in Anomaly Detection

88 - Applications 0:18:35

88 - Applications of Autoencoders - Anomaly Detection

LSTM Autoencoder for 0:07:27

LSTM Autoencoder for Anomaly Detection (Python)

Anomaly Detection Using 0:12:06

Anomaly Detection Using Autoencoders | Tensorflow | Keras

Autoencoder based Unsupervised 0:16:18

Autoencoder based Unsupervised Fault Detection || Part 3

Комментарии
Автор

❤️ Blog post with code for this video:



You will get full access to posts on Medium for $5 per month, and I will receive a portion of it. Thank you for your support!



🔥 Check out more machine learning tutorials on my website!

grabngoinfo
Автор

This tutorial is wrong. a 0.01 recall and precision are terrible result. The training part of the model should only be trained on normal data, not anomalous data.

spdazero