This article presents the project's results, focused on the simulation of civilizations that develop over time. The development is primarily influenced by three main factors: the terrain on which the tribes are initially placed, available resources, and economic aspects, such as trading with one another. The world is generated using procedural techniques, which return a world with realistic...
The interpretability of artificial neural networks (ANNs) remains a challenge, particularly as they grow deeper and incorporate millions of parameters. Kolmogorov-Arnold Networks (KANs) address this issue by using fewer parameters than traditional ANNs and representing functions as symbolic formulas, while maintaining comparable performance.
John Conway's Game of Life (GoL) serves as an...
State-space models (SSMs) have emerged as a compelling
alternative to Transformer architectures, delivering comparable
performance at significantly lower computational cost. Al-
though deterministic SSMs such as Mamba have achieved
state-of-the-art results in areas like sequence modelling and
image segmentation, their deterministic nature limits their
suitability for probabilistic...
Line Follower Algorithm for a Flying Quadcopter
Mikołaj Stasiak, Wiktor Ważny, Grzegorz Zając
Institute for Automation and Robotics, Faculty of Mechatronics, Warsaw University of Technology.
As interest in aerial drones and autonomous systems grows, so does the need for optimal solutions that can be run on minimalistic hardware. This paper describes an autonomous, vision-based...
With the increasing number of cyber threats, malware detection has become a critical challenge in cybersecurity. Traditional detection techniques, based on behavioral analysis and signature creation, present significant challenges due to their time-consuming nature and limited effectiveness against new, unknown threats. This paper explores the optimization of artificial intelligence (AI) for...
