Philippe Devienne

Weighted graphs: a tool for logic programming

Unfoldings of oriented graphs generate infinite trees that we generalize by weighting arrows of these graphs. Indexes along a branch are added during unfoldings and the result indexes variables. We study formal properties of these graphs (substitution, equivalence, unification, ...). We use them to solve the halting problem of a recursive head-rewriting rule (as in PROLOG-like languages).

Towards an spiking deep belief network for face recognition application

Understanding brain mechanisms and its problem solving techniques is the motivation of many emerging brain inspired computation methods. In this paper, respecting deep architecture of the brain and spiking model of biological neural networks, we propose a spiking deep belief network to evaluate ability of the deep spiking neural networks in face recognition application on ORL dataset. To overcome the change of using spiking neural networks in a deep learning algorithm, Siegert model is utilized as an abstract neuron model. Although there are state of the art classic machine learning algorithms for face detection, this work is mainly focused on demonstrating capabilities of brain inspired models in this era, which can be serious candidate for future hardware oriented deep learning implementations. Accordingly, the proposed model, because of using leaky integrate-and-fire neuron model, is compatible to be used in efficient neuromorphic platforms for accelerators and hardware implementation.

Temporal Refinement in Co-Design

This paper shows how it is possible to employ refinement concept of B formal method in hardware design. The structural, logical and temporal properties of a Hardware Description Language that is enriched with annotations of the Property Specification language are projected into B model. Then the generated B image is analyzed, using B method tools, in order to prove the initial properties. This technique produces a correct by design component.