Anomaly detection in deep learning can be used for fraud detection by finding abnormal patterns in data like bad credit card transactions or fake locations. Deep learning is well-suited for anomaly detection because it can learn complex patterns from large amounts of data, represent its own features that are robust to noise, and learn cross-domain patterns. Techniques for anomaly detection include unsupervised methods using autoencoder reconstruction error and supervised methods using RNNs to learn from labeled time series data and predict anomalies. Production systems for anomaly detection can use streaming data from sources like Kafka with neural networks consuming the streaming updates.

1. Anomaly Detection in Deep
Learning
Adam Gibson Skymind - Reactive Meetup 2016 @ Google Tokyo

2. What’s an “Anomaly?”
● Abnormal Patterns in Data
● Fraud Detection - “Bad credit card Transactions”
● ALSO Fraud detection - Detecting fake locations with call
detail records
● Network Intrusion - Abnormal Activity in a network
● Broken Computers in a data center

3. Brief Case Studies - eg: Why am I up here?
● Telco: http://blogs.wsj.com/cio/2016/03/14/orange-tests-deep-
learning-software-to-identify-fraud/
● Network Infrastructure: https://insights.ubuntu.
com/2016/04/25/making-deep-learning-accessible-on-
openstack/

4. Network Infra - Save time and Money avoiding
Broken workloads by auto migration before it happens

5. Why Deep Learning?
● Learns well from lots of data
● Own feature representation: Robust to noise and allows for
learning cross domain patterns
● Already applied in ads: Google itself invests lots in this same
kind of pattern recognition (targeting/relevance)

6. Techniques
● Unsupervised - Use autoencoder reconstruction error and use moving averages
use dropout with a set time window
● Supervised - RNNs Learn from a set of yes/nos in a time series. RNNs can learn
from a series of time steps and predict when an anomaly is about to occur.
● Use streaming/minibatches (all neural nets can learn like this)

7. Some definitions
● Reconstruction Error: Autoencoders can learn from
unsupervised pretraining and learn how to reconstruct data.
Minimize KL Divergence (the delta between two probability
distributions
● RNN/Time Series: See http://deeplearning4j.org/usingrnns

8. Production
● Kafka/Spark Streaming/Flink/Apex
● Neural net works as consumer of streaming updates
● Data? Mostly log ingestion, could be video

9. Questions?
Email: adam@skymind.io
Twitter: agibsonccc
Github: agibsonccc

10. Upcoming talks
Hadoop Summit: San Jose http://hadoopsummit.org/san-jose/ourspeakers/