Page not found. Your pixels are in another canvas.
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
This is a page not in th emain menu
Discussion about the article “Safe Policy Improvement with Baseline Bootstrapping in Factored Environments” by Simão, Thiago D., and Matthijs TJ Spaan. Published at Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 33. No. 01. 2019.
Discussion about the article “AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training” by Simão, Thiago D., Nils Jansen, and Matthijs TJ Spaan. Published at Proceedings of AAMAS 2021.
Summary - RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
Discussion about the article “RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction” by Kokel, Harsha, et al. Published at Proceedings of the International Conference on Automated Planning and Scheduling. Vol. 31. 2021.
Discussion about the article “Improved State Aggregation with Growing Neural Gas in Multidimensional State Spaces” by Baumann, Michael, Timo Klerx, and Hans Kleine Büning. Published at Proceedings of ERLARS (2012).
Published in 2009 International Joint Conference on Neural Networks, 2009
In this paper, the vision-based hand movement recognition problem is formulated for the universe of discourse of the Brazilian Sign Language. In order to analyze this specific domain we have used the artificial neural networks models based on distance, including neural-fuzzy models. The experiments explored here show the usefulness of these models to extract helpful knowledge about the classes of movements and to support the project of adaptative recognizer modules for Libras-oriented computational tools. Using artificial neural networks architectures - Self Organizing Maps and (Fuzzy) Learning Vector Quantization, it was possible to understand the data space and to build models able to recognize hand movements performed for one or more than one specific Libras users.
Recommended citation: Dias, D.B., Madeo, R.C.B., Rocha, T., Bíscaro, H.H., Peres, S. M. (2009). "Hand movement recognition for brazilian sign language: a study using distance-based neural networks." 2009 International Joint Conference on Neural Networks. https://ieeexplore.ieee.org/abstract/document/5178917/
Published in Proceedings of the 2010 ACM Symposium on Applied Computing, 2010
In several countries, deaf communities adopt the sign language as their official and natural language. This fact inserts a new field for the software application development that can improve sign language dissemination and social inclusion of deaf people. Alphabetic character-based applications, like games and educational softwares, can be adapted to run as fingerspelling-based applications, in which the inputs are signs (static images or videos) rather than letters (typed letters). In this paper, we present a Pattern Recognition Module, implemented by Committee Machine, for fingerspelling applications. The committee experts are built with supervised and unsupervised Fuzzy Learning Vector Quantization models using the” boosting by filtering” strategy. The module was tested in a specific sign language context considering hand configurations and hand movements.
Recommended citation: Madeo, R.C.B., Peres, S. M., Bíscaro, H.H., Dias, D.B., Boscarioli, C. (2010). "A committee machine implementing the pattern recognition module for fingerspelling applications." Proceedings of the 2010 ACM Symposium on Applied Computing. https://dl.acm.org/doi/abs/10.1145/1774088.1774287
Published in Proceedings of the 12th international ACM SIGACCESS conference on Computers and accessibility, 2010
This paper presents an approach for carrying out gesture recognition for the Brazilian Sign Language Manual Alphabet. The gestural patterns are treated as a combination of three primitives, or cheremes-hand configuration, hand orientation and hand movement. The recognizer is built in a modular architecture composed by inductive reasoning modules, which use the artificial neural network Fuzzy Learning Vector Quantization; and rule-based modules. This architecture has been tested and results are presented here. Some strengths of such approach are: robustness of recognition, portability to similar contexts, extensibility of the dataset to be recognize and reduction of the vocabulary recognition problem to the recognition of its primitives.
Recommended citation: Madeo, R.C.B., Peres, S. M., Dias, D.B., Boscarioli, C. (2010). "Gesture recognition for fingerspelling applications: an approach based on sign language cheremes." Proceedings of the 12th international ACM SIGACCESS conference on Computers and accessibility. https://dl.acm.org/doi/abs/10.1145/1878803.1878861
Algoritmos bio-inspirados aplicados ao reconhecimento de padrões da libras: enfoque no parâmetro movimento
Published in University of São Paulo (Undergraduate thesis), 2010
This work analised the characteristics of the “movement” parameter on the Brazilian Sign Language (Libras) and study Bio-inspired computation algorithms that could be used to detect these moviments through pattern recognition.
Programação dinâmica em tempo real para processos de decisão markovianos com probabilidades imprecisas
Published in University of São Paulo (Master Thesis), 2014
Master thesis about Asynchronous Dynamic Programming approches for Markov Decision Processes with Imprecise Probabilities.
Recommended citation: Dias, Daniel B. (2014). "Programação dinâmica em tempo real para processos de decisão markovianos com probabilidades imprecisas." Master Thesis. https://www.teses.usp.br/teses/disponiveis/45/45134/tde-21012015-083016/publico/dissertacao.pdf
Published in Artificial Intelligence, 2014
Markov Decision Processes have become the standard model for probabilistic planning. However, when applied to many practical problems, the estimates of transition probabilities are inaccurate. This may be due to conflicting elicitations from experts or insufficient state transition information. The Markov Decision Process with Imprecise Transition Probabilities (MDP-IPs) was introduced to obtain a robust policy where there is uncertainty in the transition. Although it has been proposed a symbolic dynamic programming algorithm for MDP-IPs (called SPUDD-IP) that can solve problems up to 22 state variables, in practice, solving MDP-IP problems is time-consuming. In this paper we propose efficient algorithms for a more general class of MDP-IPs, called Stochastic Shortest Path MDP-IPs (SSP MDP-IPs) that use initial state information to solve complex problems by focusing on reachable states. The (L)RTDP-IP algorithm, a (Labeled) Real Time Dynamic Programming algorithm for SSP MDP-IPs, is proposed together with three different methods for sampling the next state. It is shown here that the convergence of (L)RTDP-IP can be obtained by using any of these three methods, although the Bellman backups for this class of problems prescribe a minimax optimization. As far as we are aware, this is the first asynchronous algorithm for SSP MDP-IPs given in terms of a general set of probability constraints that requires non-linear optimization over imprecise probabilities in the Bellman backup. Our results show up to three orders of magnitude speedup for (L)RTDP-IP when compared with the SPUDD-IP algorithm.
Recommended citation: Delgado, K.V., De Barros, L.N., Dias, D.B., Sanner, S. (2016). "Real-time dynamic programming for Markov decision processes with imprecise probabilities." Artificial Intelligence. https://www.sciencedirect.com/science/article/pii/S0004370215001411
Talk with Renata Madeo and Sarajane Peres to present a business plan to build a LIBRAS (Brazilian Sign Language) Hangman game. This project won the third place on Social and Environmental category.
Poster presentation about the work “Algoritmos bio-inspirados aplicados ao reconhecimento de padrões da LIBRAS: enfoque no parâmetro movimento”, that later became my undergratuation thesis.
Poster presentation about the work “Hand Movement Recognition for Brazilian Sign Language: A Study Using Distance-Based Neural Networks”, that became the basis of my undergratuation thesis.