10 papers
Łukasiewicz Neural Networks Extended: Residual Architectures and Crystallization Strategies for Interpretable Rule Extraction
Carlos Leandro
A feed-forward neural network whose weights are integers and whose activation is the truncated identity implements, neuron by neuron, the connectives of Łukasiewicz many-valued log…
Categorical semiotics: Foundations for Knowledge Integration
Carlos Leandro
The integration of knowledge extracted from diverse models, whether described by domain experts or generated by machine learning algorithms, has historically been challenged by the…
The Actias system: supervised multi-strategy learning paradigm using categorical logic
Carlos Leandro, Helder Pita, Luís Monteiro
One of the most difficult problems in the development of intelligent systems is the construction of the underlying knowledge base. As a consequence, the rate of progress in the dev…
Multibody minimum-energy trajectory with applications to protein folding
Carlos Leandro, Jorge Ambrósio
This work addresses the optimal control of multibody systems being actuated with control forces in order to find a dynamically feasible minimum-energy trajectory of the system. The…
Symbolic Knowledge Extraction using Łukasiewicz Logics
Carlos Leandro
This work describes a methodology that combines logic-based systems and connectionist systems. Our approach uses finite truth-valued Łukasiewicz logic, wherein every connective can…
Patterns on data described by vague limits, vague colimits and vague commutativity
Carlos Leandro, Luís Monteiro
The development of machine learning in particular and artificial intelligent in general has been strongly conditioned by the lack of an appropriated framework to specify and integr…