INESC-ID

About: INESC-ID is a nonprofit organization based out in Lisbon, Portugal. It is known for research contribution in the topics: Computer science & Context (language use). The organization has 932 authors who have published 2618 publications receiving 37658 citations.

The MATISSE MATLAB compiler

Abstract: This paper describes MATISSE, a MATLAB to C compiler targeting embedded systems that is based on Strategic and Aspect-Oriented Programming concepts. MATISSE takes as input: (1) MATLAB code and (2) LARA aspects related to types and shapes, code insertion/removal, and specialization based directives defining default variable values. In this paper we also illustrate the use of MATISSE in leveraging data types and shapes to generate customized C code suitable for high-level hardware synthesis tools. The preliminary experimental results presented here reveal the described approach to yield performance results for the resulting hardware and software references implementations that are comparable in terms of performance with hand-crafted solutions but derived automatically at a fraction of the cost.

Analysis of Inverse Reinforcement Learning with Perturbed Demonstrations

Abstract: Inverse reinforcement learning (IRL) addresses the problem of recovering the unknown reward function for a given Markov decision problem (MDP) given the corresponding optimal policy or a perturbed version thereof. This paper studies the space of possible solutions to the general IRL problem, when the agent is provided with incomplete/imperfect information regarding the optimal policy for the MDP whose reward must be estimated. We focus on scenarios with finite state-action spaces and discuss the constraints imposed on the set of possible solutions when the agent is provided with (i) perturbed policies; (ii) optimal policies; and (iii) incomplete policies. We discuss previous works on IRL in light of our analysis and show that, with our characterization of the solution space, it is possible to determine non-trivial closed-form solutions for the IRL problem. We also discuss several other interesting aspects of the IRL problem that stem from our analysis.

PIT-ProcessM: A Software Process Improvement Meta-Model

Abstract: Software Process Improvement (SPI) is one of the main actual software development challenges. Process metamodels allow capturing informational and behavioural aspects of software development processes. Unfortunately, standard process meta-modelling approaches, such as the Software Process Engineering Meta-model (SPEM), OPEN Process Framework (OPF) and Standard Meta-model for Software Development Methodologies (SMSDM), focus just on process description, providing different models for several versions of the same process. According to these meta modelling approaches, it is not possible to compare and identify improvements in an improved process. This lack of information recognizes that further research in SPI meta-model is needed to reflect the evolution/change on software processes. Considering this limitation in SPI meta-modelling, this paper presents a comparative study of the most recognized process meta-models approaches and introduces a new SPI based meta-model designed by Project IT-Process Meta-model (PIT-Process M). Our intention is to present observed problems in existing approaches and propose a process meta-model that addresses features related to process changes and evolution.

Pseudo-fractional ARMA modelling using a double levinson recursion

Abstract: The modelling of fractional linear systems through ARMA models is addressed. To perform this study, a new recursive algorithm for impulse response ARMA modelling is presented. This is a general algorithm that allows the recursive construction of ARMA models from the impulse response sequence. This algorithm does not need an exact order specification, as it gives some insights into the correct orders. It is applied to modelling fractional linear systems described by fractional powers of the backward difference and the bilinear transformations. The analysis of the results leads to propose suitable models for those systems.