Presented By O'Reilly and Cloudera
Make Data Work
22–23 May 2017: Training
23–25 May 2017: Tutorials & Conference
London, UK

Video anomaly detection with self-supervised deep nets

Arshak Navruzyan (Startup.ML)
17:2518:05 Wednesday, 24 May 2017
Data science and advanced analytics
Location: Capital Suite 7
Level: Intermediate
Average rating: ****.
(4.80, 5 ratings)

Who is this presentation for?

  • Security professionals, chief security officers, and data scientists

Prerequisite knowledge

  • General knowledge of machine learning and information security

What you'll learn

  • Explore the current state of the art for video analysis using deep learning techniques and the associated challenges

Description

Factories could improve worker safety and reduce costs from machine, robot, and worker error through incisive use of state-of-the-art video deep learning techniques. Specifically, deep learning can be used to detect anomalies in video recordings of factory workers. Such anomalies may include faults in the machines, worker behavior, improper use of safety uniforms, and anomalies in robot performance.

Deep learning affords novel and powerful techniques for video prediction and analysis. Arshak Navruzyan explores the current state of the art for video analysis using deep learning techniques and the associated challenges.

Photo of Arshak Navruzyan

Arshak Navruzyan

Startup.ML

Arshak Navruzyan is a machine-learning-focused product manager and the founder of Startup.ML, a machine-learning fellowship program that has graduated over 30 data scientists now employed by companies including Uber, Facebook, and Baidu. Arshak has delivered AI solutions for multibillion dollar quantitative hedge funds, numerous venture-funded startups, and some of the largest telecoms in the world and has held technology leadership roles at Argyle Data, Alpine Data Labs, and Endeca/Oracle.