Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.

Anomaly detection in deep learning

10.126 visualizaciones

Publicado el

Brief presentation on anomaly detection with deep learning.

Publicado en: Datos y análisis

Anomaly detection in deep learning

  1. 1. Anomaly Detection in Deep Learning Adam Gibson Skymind - Reactive Meetup 2016 @ Google Tokyo
  2. 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. 3. Brief Case Studies - eg: Why am I up here? ● Telco: learning-software-to-identify-fraud/ ● Network Infrastructure: https://insights.ubuntu. com/2016/04/25/making-deep-learning-accessible-on- openstack/
  4. 4. Network Infra - Save time and Money avoiding Broken workloads by auto migration before it happens
  5. 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. 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. 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
  8. 8. Production ● Kafka/Spark Streaming/Flink/Apex ● Neural net works as consumer of streaming updates ● Data? Mostly log ingestion, could be video
  9. 9. Questions? Email: Twitter: agibsonccc Github: agibsonccc
  10. 10. Upcoming talks Hadoop Summit: San Jose