6 papers
Explaining Digital Pathology Models via Clustering Activations
Adam Bajger, Jan Obdržálek, VojtÄch Kůr +4
We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used methods based on saliency maps, suc…
Multiagent Stochastic Shortest Path Problem
Martin Jonáš, AntonÃn KuÄera, VojtÄch Kůr +2
We introduce and study the multi-agent stochastic shortest path (MSSP) problem, in which agents strive to reach a target state, aiming to minimize the expected time to reach th…
Memory Assignment for Finite-Memory Strategies in Adversarial Patrolling Games
VojtÄch Kůr, VÃt Musil, VojtÄch Åehák
Adversarial Patrolling games form a subclass of Security games where a Defender moves between locations, guarding vulnerable targets. The main algorithmic problem is constructing a…
LLEXICORP: End-user Explainability of Convolutional Neural Networks
VojtÄch Kůr, Adam Bajger, Adam KukuÄka +3
Convolutional neural networks (CNNs) underpin many modern computer vision systems. With applications ranging from common to critical areas, a need to explain and understand the mod…
Steady-State Strategy Synthesis for Swarms of Autonomous Agents
Martin Jonáš, AntonÃn KuÄera, VojtÄch Kůr +1
Steady-state synthesis aims to construct a policy for a given MDP such that the long-run average frequencies of visits to the vertices of satisfy given numerical constraint…
Multiple Mean-Payoff Optimization under Local Stability Constraints
David KlaÅ¡ka, AntonÃn KuÄera, VojtÄch Kůr +2
The long-run average payoff per transition (mean payoff) is the main tool for specifying the performance and dependability properties of discrete systems. The problem of constructi…