IRIS-HEP Fellow: Eric Moreno
Fellowship dates: Jun – Aug, 2021
Home Institution: MIT
Project: Anomaly Detection with Spiking Neural NetworksSpiking Neural Networks (SNNs) mimic organic systems like the human brain with asynchronous spikes, bridging the gap between artificial and biological intelligence and excelling at temporally-dependent data. The inherent strengths of these SNNs are extremely useful at the Large Hadron Collider (LHC) with their need for fast inference and accurate data-processing of petabytes of time-series events. This project involves the development of an anomaly detection algorithm based on SNNs and Autoencoders, which learn to identify outlier events in an unsupervised manner. This algorithm will complement LHC scientists in their search for beyond-standard-model physics, delivering a list of previously unidentified anomalous events.
More information: My project proposal
Maurizio Pierini - (CERN)
Jean-Roch Vlimant - (Caltech)
- 27 Oct 2021 - "Anomaly Detection with Spiking Neural Networks", Eric Moreno, IRIS-HEP Topical Meetings Recording: Anomaly Detection with Spiking Neural Networks