Search

The evolvable hardware paradigm facilitates the construction of autonomous systems that can adapt to environmental changes and degrading effects in the computational resources. Extending these scenarios, we study the capability of evolvable hardware classifiers to adapt to intentional run-time fluctuations in the available resources, i.e., chip area, in this work. To that end, we leverage the Functional Unit Row (FUR) architecture, a coarse-grained reconfigurable classifier, and apply it to two medical benchmarks, the Pima and Thyroid data sets from the UCI Machine Learning Repository. We show that FUR΄s classification performance remains high during changes of the utilized chip area and that performance drops are quickly compensated for. Additionally, we demonstrate that FUR΄s recovery capability benefits from extra resources. [ABSTRACT FROM AUTHOR]

In this paper we investigate whether multi-objective evolution of digital hardware components has advantages over single-objective evolution in terms of convergence and robustness. To that end, we experimentally compare a standard genetic algorithm to several multi-objective optimizers on a set of test problems. The results show that, for more complex test problems, the multi-objective optimizers TSPEA2 and NSGAII indeed outperform the single-objective genetic algorithm as they more often evolve correct circuits, and mostly with less computational effort. [ABSTRACT FROM AUTHOR]

We analyze and compare four different evolvable hardware approaches for classification tasks: An approach based on a programmable logic array architecture, an approach based on two-phase incremental evolution, a generic logic architecture with automatic definition of building blocks, and a specialized coarse-grained architecture with pre-defined building blocks. We base the comparison on a common data set and report on classification accuracy and training effort. The results show that classification accuracy can be increased by using modular, specialized classifier architectures. Furthermore, function level evolution, either with predefined functions derived from domain-specific knowledge or with functions that are automatically defined during evolution, also gives higher accuracy. Incremental and function level evolution reduce the search space and thus shortens the training effort. [ABSTRACT FROM AUTHOR]

Evolutionary hardware design reveals the potential to provide autonomous systems with self-adaptation properties. We first outline an architectural concept for an intrinsically evolvable embedded system that adapts to slow changes in the environment by simulated evolution, and to rapid changes in available resources by switching to preevolved alternative circuits. In the main part of the paper, we treat evolutionary circuit design as a multi-objective optimization problem and compare two multi-objective optimizers with a reference genetic algorithm. In our experiments, the best results were achieved with TSPEA2, an optimizer that prefers a single objective while trying to maintain diversity. [ABSTRACT FROM AUTHOR]