Search Results for author: Peter Bajcsy

Found 6 papers, 3 papers with code

AI Model Utilization Measurements For Finding Class Encoding Patterns

no code implementations12 Dec 2022 Peter Bajcsy, Antonio Cardone, Chenyi Ling, Philippe Dessauw, Michael Majurski, Tim Blattner, Derek Juba, Walid Keyrouz

We approach the problems by introducing theoretical underpinnings of AI model utilization measurement and understanding patterns in utilization-based class encodings of traffic signs at the level of computation graphs (AI models), subgraphs, and graph nodes.

Self-Driving Cars

Baseline Pruning-Based Approach to Trojan Detection in Neural Networks

2 code implementations22 Jan 2021 Peter Bajcsy, Michael Majurski

Next, measure the accuracy of a set of systematically pruned NN models following multiple pruning schemas.

QUAREP-LiMi: A community-driven initiative to establish guidelines for quality assessment and reproducibility for instruments and images in light microscopy

no code implementations21 Jan 2021 Glyn Nelson, Ulrike Boehm, Steve Bagley, Peter Bajcsy, Johanna Bischof, Claire M Brown, Aurelien Dauphin, Ian M Dobbie, John E Eriksson, Orestis Faklaris, Julia Fernandez-Rodriguez, Alexia Ferrand, Laurent Gelman, Ali Gheisari, Hella Hartmann, Christian Kukat, Alex Laude, Miso Mitkovski, Sebastian Munck, Alison J North, Tobias M Rasse, Ute Resch-Genger, Lucas C Schuetz, Arne Seitz, Caterina Strambio-De-Castillia, Jason R Swedlow, Ioannis Alexopoulos, Karin Aumayr, Sergiy Avilov, Gert-Jan Bakker, Rodrigo R Bammann, Andrea Bassi, Hannes Beckert, Sebastian Beer, Yury Belyaev, Jakob Bierwagen, Konstantin A Birngruber, Manel Bosch, Juergen Breitlow, Lisa A Cameron, Joe Chalfoun, James J Chambers, Chieh-Li Chen, Eduardo Conde-Sousa, Alexander D Corbett, Fabrice P Cordelieres, Elaine Del Nery, Ralf Dietzel, Frank Eismann, Elnaz Fazeli, Andreas Felscher, Hans Fried, Nathalie Gaudreault, Wah Ing Goh, Thomas Guilbert, Roland Hadleigh, Peter Hemmerich, Gerhard A Holst, Michelle S Itano, Claudia B Jaffe, Helena K Jambor, Stuart C Jarvis, Antje Keppler, David Kirchenbuechler, Marcel Kirchner, Norio Kobayashi, Gabriel Krens, Susanne Kunis, Judith Lacoste, Marco Marcello, Gabriel G Martins, Daniel J Metcalf, Claire A Mitchell, Joshua Moore, Tobias Mueller, Michael S Nelson, Stephen Ogg, Shuichi Onami, Alexandra L Palmer, Perrine Paul-Gilloteaux, Jaime A Pimentel, Laure Plantard, Santosh Podder, Elton Rexhepaj, Arnaud Royon, Markku A Saari, Damien Schapman, Vincent Schoonderwoert, Britta Schroth-Diez, Stanley Schwartz, Michael Shaw, Martin Spitaler, Martin T Stoeckl, Damir Sudar, Jeremie Teillon, Stefan Terjung, Roland Thuenauer, Christian D Wilms, Graham D Wright, Roland Nitschke

In April 2020, the QUality Assessment and REProducibility for Instruments and Images in Light Microscopy (QUAREP-LiMi) initiative was formed.

Scientific Calculator for Designing Trojan Detectors in Neural Networks

1 code implementation5 Jun 2020 Peter Bajcsy, Nicholas J. Schaub, Michael Majurski

This work presents a web-based interactive neural network (NN) calculator and a NN inefficiency measurement that has been investigated for the purpose of detecting trojans embedded in NN models.

Cannot find the paper you are looking for? You can Submit a new open access paper.