Kalman Pusztai

Learn More
Labeling training data for machine learning algorithms is tedious, time consuming, and error prone. Consequently, it is of utmost importance to minimize the amount of labeled data that is required to learn a target concept. In the work presented here, I focus on reducing the need for labeled data in multi-view learning tasks. The key characteristic of(More)
While on the move, the surrounding environment of a mobile application may change quite often. The mobile applications have to be able to properly react to the context changes. The common approach to deal with the application adaptation is based on rules. For each action one must specify the set of rules that triggers the action when the context changes. In(More)
The Unified Software Development Process (USDP) and UML have been now generally accepted as the standard methodology and modeling language for developing ObjectOriented Systems. Although Agent-based Systems introduces new issues, we consider that USDP and UML can be used in an extended manner for modeling Agent-based Systems. The paper presents a(More)
Designing and architecting new routing protocols is an expensive task, because they are complex systems managing distributed network state, in order to create and maintain the routing databases. Existing routing protocol implementations are compact, bundling together a database, an optimal path calculation algorithm and a network state distribution(More)
One of the steps involved in the computer-aided design for FPGA (FieldProgrammable Gate Array) circuits is placement. In this step, the logic functions are assigned to specific cells of the circuit. In conventional hierarchical min-cut based placement algorithms, the layout region is bi-partitioned using slicing lines in a top-down manner. In these(More)