This is part of Machine Learning-Driven Anomaly Detection
What you will learn
It can also be described as multi-variate time series data. This kind of data has temporal as well as spatial correlation between the different variables. They are the most complex among the 4 categories of data. Most of the good solutions are based on deep learning.
We will review a set of deep learning papers highlighting their salient points for anomaly detection solution. Most of the solution is based on a combination of a recurrent network (RNN) and an autoencoder network (AE). RNN handles temporal correlation and AE handles spatial correlation.
- Paper: “Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network” by Su, Zhao
- Paper: “Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model” by Filonov, Lavrentyev
- Paper: “LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection” by Malhotra, Ramakrishnan
- Paper: “A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder” by Park, Hoshi
This is a FREE class!
Can’t make it to live session? No worries. Go ahead and register; we will send you the session recording.
See below for past session recordings & notes
COO, CIO, DevOps, Software Engineers
- Must have: Development experience
- Nice to have: Python knowledge
What to Bring
- Please bring a reasonably modern laptop (Corporate laptops with overly restrictive firewalls may not work well; Personal laptops are recommended)
- [nice to have] download our docker image elephantscale/es-training
- Class Notes here
Pranab Ghosh is a Data Science Consultant, He owns several open-source Big Data and Data Science projects using Hadoop, Spark, Storm, Kafka, NoSQL databases, and the related ecosystem.