• Hierarchical Detection Network

    Multi-object detection
  • Progressive Data Transmission

    Cloud Computing
  • Location Registration and Recognition

    Aligning CT nodule neighborhoods
  • Likelihood Ratio Vesselness

    Retinal Vessel Extraction
Michal Sofka  
Michal Sofka Range Data

Michal Sofka is a Principal Scientist at 4Catalyzer.
Between 2013 and 2015, he was a Sr. Technical Leader in Cisco's Security Business Group. His research focused on large scale machine learning for threat defense.
Prior to Cisco, Michal was a research scientist and R&D manager at Siemens Corporation, Corporate Research (SCCT), Princeton, NJ. Michal did his undergraduate work at the Czech Technical University. He received the MS degree in Electrical Engineering from Union College in 2001. He received the MS and PhD degrees in Computer Science from the Rensselaer Polytechnic Institute (RPI) in 2006 and 2008, respectively.

Learning detectors of malicious network traffic. Multiple Instance Learning using weakly labeled data and new robust representation.
One page summary of security publications.

Representation of Network Traffic (Usenix 2016)
Detection and Measurement (TMI 2014)
Tubular Structure Detection (IPMI 2013)
IntellEditS editing (MICCAI 2013)

4/27/2017 Paper on our work accepted to MICCAI 2017.
3/15/2017 Paper on learning discretizations via convex optimization accepted to the Machine Learning journal.
2/15/2017 Butterfly Network sponsors 2017 Medical Image Computing and Computer Assisted Intervention (MICCAI) conference.
10/17/2017 Butterfly Network sponsors Deep Learning in Medical Imaging at MICCAI 2016.

Copyright 2017 Michal Sofka