169,885 research outputs found
Resilience of Deep Learning Applications: Where We are and Where We Want to Go
No full textDeep Learning (DL) [1] is currently one of the most intensively and widely used predictive models in the field of machine learning. DL has proven to give very good results for many complex tasks and applications, such as object recognition in images/videos, natural language processing, robotics, aerospace, smart healthc are, and autonomous driving. Nowa-days, there is intense activity in designing custom Artificial Intelligence (AI) hardware accelerators to support the energy-hungry data movement, speed of computation, and memory resources that DL requires to realize its full potential [2]. Furthermore, there is an incentive to migrate AI from cloud to edge devices, i.e., Internet-of- Things devices, to address data confidentiality issues and bandwidth limitations, and also to alleviate the communication latency, especially for real-time safety-critical decisions, e.g., in autonomous driving
Aiming for an Online/ Onsite Format and Finally Moving to Online Only
No full textBased on the past two years of experience as an online event due to the Covid-19 outbreak, DATE 2022 has been planned to cope with the uncertainty of the situation, having two days onsite, in Antwerp, Belgium, from March 14 to 15, 2022, to be followed by an online program until March 23, 2022. A different organization and format had been adopted to engage the DATE community, with a two-day rich program and numerous talks and panels to gather again, in person. The scientific program online had been completed by live panels and presentations to offer a valuable virtual experience. Unfortunately, for the third year in a row, DATE moved to a completely virtual event, which nevertheless attracted a broad audience.status: Published onlin
FSM fault models impact on test performances
No full textAim of this paper is the analysis of different functional fault models for multi-level implementations of sequential circuits. The relationships between functional and gate level fault coverage are fully discussed
Context-Driven Data Filtering: A Methodology
No full textThe goal of this paper is the introduction of a methodology for designing context-driven data selection, that is the possibility to tailor the available, usually too rich, data to be held on portable mobile devices, according to context. First of all, we will introduce the concept of context and its model, a data structure that expresses knowledge on the user, the environment and the possible scenarios. We will then focus on the proposed methodology for selecting, by means of such information, the relevant data to be made available on a user device. An application of the proposed methodology is the possibility to select data of interest for portable devices, where computation, memory, power and connectivity resources are limited, and thus, tailororing the available, usually too rich, data according to context is a mandatory task
A design methodology for the correct specification of VLSI systems
No full textTime to market is a key factor to beat competitors as it measures the ability to satisfy the market demands at the proper time. Innovative design methodologies based on formal methods can positively affect this parameter allowing rigour of design practice and guaranteeing correctness of implementations. In this paper we introduce the methodological approach based on the use of the specification language VHDL/S and of the related formal based tools. The final goal is to provide an environment able to support the designer in the specification phase with the generation of correct and verified VHDL code. The integration of this formal based design phase into a standard CAD design flow is managed through the restriction to the VHDL subset supporting logical synthesis. Finally the encapsulation into a commercial CAD framework guarantees the unified approach to design required by final users
A data mining approach to incremental adaptive functional diagnosis
No full textThis paper presents a novel approach to functional fault diagnosis adopting data mining to exploit knowledge extracted from the system model. Such knowledge puts into relation test outcomes with components failures, to define an incremental strategy for identifying the candidate faulty component. The diagnosis procedure is built upon a set of sorted, possibly approximate, rules that specify given a (set of) failing test, which is the faulty candidate. The procedure iterative selects the most promising rules and requests the execution of the corresponding tests, until a component is identified as faulty, or no diagnosis can be performed. The proposed approach aims at limiting the number of tests to be executed in order to reduce the time and cost of diagnosis. Results on a set of examples show that the proposed approach allows for a significant reduction of the number of executed tests (the average improvement ranges from 32% to 88%)
Board-level functional fault diagnosis using data mining
No full textThis paper presents an approach for performing functional diagnosis of complex systems by means of data mining. The technique allows to derive a set of rules from a functional model of the system for efficiently driving the diagnosis procedure towards the identification of the most promising faulty candidate. The approach is adopted within an incremental method, to limit the number of tests to be performed, thus reducing costs and effort
Two-Dimensional Sequential Array Architectures: Design for Testability and Reconfiguration Issues
No full textNew Design for Testability techniques aimed both at overcoming the problem of testing array architectures composed of sequential cells and at guaranteeing fault tolerance through reconfiguration are proposed
A BDD based algorithm for detecting difficult faults
No full textThe aim of this paper is the presentation of a new method- ologyforfast testpattern generationfir difficultfaults. A BDD-based algorithm is applied as back-end of a standard A TPG (e.g. SOCRATES, FAN, PODEM) thusproviding a solution to their ineficiency in difficult faults analysis. Experimental results show the effectiveness of the proposed approachon a number of benchmark circuits
Emergent Semantics and Cooperation in Multi-Knowledge Environments: the ESTEEM Architecture
No full textIn the present global society, information has to be exchangeable in open and dynamic environments, where interacting peers do not necessarily share a common understanding of the world at hand, and do not have a complete picture of the context where the interaction occurs. In this paper, we present the Esteem approach and the related peer architecture for emergent semantics in dynamic and multi-knowledge environments. In Esteem, semantic communities are built around declared interests in the form of manifesto ontologies, and their autonomous nature is preserved by allowing a shared semantics to naturally emerge from peer interactions
- …
