Anomaly Detection meets
Deep Learning

Berkeley Statistics and Machine Learning Forum

Find the slides at slides.com/eiffl/ano

On the menu today

  • Auto-Encoders
  • GANs
  • Likelihood-Based models

Disclaimer: This is NOT an exhaustive review, there are many hundreds of anomaly detection papers out there

 

Also, remember our session last year led by Ben Nachman

The AutoEncoder Approach

Variational Autoencoder based Anomaly Detection

An & Cho 2015

The simple  autoencoder approach

The Variational AutoEncoder

Because a number of samples are drawn from the latent variable distribution, this allows the reconstruction probability to take into account the variability of the latent variable space, which is one of the main distinctions between the proposed method and the autoencoder based anomaly detection.

Difference from an autoencoder based anomaly detection

  • Latent variables are stochastic variables, capturing not only means but also variance of the model
  • Reconstructions are stochastic variables, capturing variance of the signal
  • Reconstructions are probability measures, can incorporate heterogenous data 

Experiments

Applications in Particle Physics

Another interesting paper using autoencoders with a latent space model

Latent Space Autoregression for Novelty Detection, Abati et al. 2019

Are autoencoders so great?

Anomaly Detection,
the GAN way

Unsupervised Anomaly Detection with
Generative Adversarial Networks to Guide Marker Discovery

The idea

Building an anomaly score

  • Mapping new images to latent space by minimizing the residual loss:

     
  • And a discrimination loss:


     
  • For each image x, z is optimized to minimize:

 

 

This loss after optimization will be the anomaly score

Experiments

Application on astronomical images

Work led by the amazing Kate Storey-Fisher (NYU) @kstoreyf

Real HSC images

GAN generated images

Low and high anomaly scores

Anomaly Detection with Likelihood models

DETECTING OUT-OF-DISTRIBUTION INPUTS TO DEEP
GENERATIVE MODELS USING TYPICALITY

Nalisnick et al. 2019

I recommend checking out this great set of slides:
 http://www.gatsby.ucl.ac.uk/~balaji/mluq-talk-balaji.pdf

Anomaly Detection meetsDeep Learning

By eiffl

Anomaly Detection meetsDeep Learning

Session of the BIDS ML & Stats forum on anomaly detection

  • 969