Tesis sobre el tema "Interpretable By Design Architectures"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Interpretable By Design Architectures".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Jeanneret, Sanmiguel Guillaume. "Towards explainable and interpretable deep neural networks". Electronic Thesis or Diss., Normandie, 2024. http://www.theses.fr/2024NORMC229.
Texto completoDeep neural architectures have demonstrated outstanding results in a variety of computer vision tasks. However, their extraordinary performance comes at the cost of interpretability. As a result, the field of Explanable AI has emerged to understand what these models are learning as well as to uncover their sources of error. In this thesis, we explore the world of explainable algorithms to uncover the biases and variables used by these parametric models in the context of image classification. To this end, we divide this thesis into four parts. The first three chapters proposes several methods to generate counterfactual explanations. In the first chapter, we proposed to incorporate diffusion models to generate these explanations. Next, we link the research areas of adversarial attacks and counterfactuals. The next chapter proposes a new pipeline to generate counterfactuals in a fully black-box mode, \ie, using only the input and the prediction without accessing the model. The final part of this thesis is related to the creation of interpretable by-design methods. More specifically, we investigate how to extend vision transformers into interpretable architectures. Our proposed methods have shown promising results and have made a step forward in the knowledge frontier of current XAI literature
Kumar, Rakesh. "Holistic design for multi-core architectures". Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2006. http://wwwlib.umi.com/cr/ucsd/fullcit?p3222991.
Texto completoTitle from first page of PDF file (viewed September 20, 2006). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 182-193).
Poyias, Kyriakos. "Design-by-contract for software architectures". Thesis, University of Leicester, 2014. http://hdl.handle.net/2381/28924.
Texto completoShao, Yakun. "Design and Modeling of Specialized Architectures". Thesis, Harvard University, 2016. http://nrs.harvard.edu/urn-3:HUL.InstRepos:33493560.
Texto completoEngineering and Applied Sciences - Computer Science
Davies, Daniel. "Representation of multiple engineering viewpoints in Computer Aided Design through computer-interpretable descriptive markup". Thesis, University of Bath, 2008. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.488893.
Texto completoIppolito, Corey A. "Software architectures for flight simulation". Thesis, Georgia Institute of Technology, 2000. http://hdl.handle.net/1853/15749.
Texto completoNuzman, Joseph. "Memory subsystem design for explicit multithreading architectures". College Park, Md. : University of Maryland, 2003. http://hdl.handle.net/1903/146.
Texto completoThesis research directed by: Dept. of Electrical and Computer Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
Smith, Richard Bartlett. "Design and integrity of deterministic system architectures". Thesis, University College London (University of London), 2007. http://discovery.ucl.ac.uk/1445115/.
Texto completoRoomi, Akeel S. "Multiprocessor computer architectures : algorithmic design and applications". Thesis, Loughborough University, 1989. https://dspace.lboro.ac.uk/2134/10872.
Texto completoDasgupta, Sohini. "Formal design and synthesis of GALS architectures". Thesis, University of Newcastle Upon Tyne, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.446196.
Texto completoLee, Andrew Sui Tin. "Design of future optical ring network architectures". Thesis, University of Strathclyde, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.415308.
Texto completoIbrahim, Jihad E. "Algorithms and Architectures for UWB Receiver Design". Diss., Virginia Tech, 2007. http://hdl.handle.net/10919/26105.
Texto completoPh. D.
BOZZOLI, LUDOVICA. "New Design Techniques for Dynamic Reconfigurable Architectures". Doctoral thesis, Politecnico di Torino, 2021. http://hdl.handle.net/11583/2934684.
Texto completoIsmailoglu, Ayse Neslin. "Asynchronous Design Of Systolic Array Architectures In Cmos". Phd thesis, METU, 2008. http://etd.lib.metu.edu.tr/upload/12609443/index.pdf.
Texto completothe method is technology independent and robust against all physical and environmental variations. To demonstrate the verification method, adders are selected for being at the core of data processing systems. Two asynchronous adder topologies in the delay-insensitive dual-rail threshold logic style, having data-dependent early carry evaluation paths, are converted into bit-level pipelined systolic arrays. On these adders, data-dependent delay-insensitivity violations are detected and resolved using the proposed verification technique. The modified adders achieved the targeted O(log2n) average completion time and -as a result of bit-level pipelining- nearly constant throughput against increased bit-length. The delay-insensitivity verification method could further be extended to handle more early output evaluation paths in multi-dimension.
Schlutz, Jürgen [Verfasser]. "Conceptual Design of Lunar Exploration Architectures / Jürgen Schlutz". München : Verlag Dr. Hut, 2012. http://d-nb.info/1022535749/34.
Texto completoMcGovern, Brian Patrick. "The systematic design of VLSI signal processing architectures". Thesis, Queen's University Belfast, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.333841.
Texto completoPerreault, David John. "Design and evaluation of cellular power converter architectures". Thesis, Massachusetts Institute of Technology, 1997. http://hdl.handle.net/1721.1/10452.
Texto completoIncludes bibliographical references (p. 155-160).
by David John Perreault.
Ph.D.
Ahmed, Mohamed Hassan Abouelella. "Power Architectures and Design for Next Generation Microprocessors". Diss., Virginia Tech, 2019. http://hdl.handle.net/10919/103175.
Texto completoDoctor of Philosophy
With the rapid increase of cloud computing and the high demand for digital content, it is estimated that the power consumption of the IT industry will reach 10 % of the total electric power in the USA by 2020. Multi-core processors (CPUs) and graphics processing units (GPUs) are the key elements in fulfilling all of the digital content requirements but come with a price of more power-hungry processors, driving the power per server rack to 20 KW levels. The need for more efficient power management solutions on the architecture level, down to the converter level, is inevitable. The data center manufacturers have recently adopted a more efficient architecture that supplies a 48V DC server rack distribution instead of a 12V DC distribution to the server motherboard. This helped reduce costs and losses, but as a consequence, raised a challenge in the design of the DC/DC voltage regulator modules (VRM) supplied by the 48V, in order to power the CPU and GPU. In this work, different architectures will be explored for the 48V VRM, and the trade-off between them will be evaluated. The main target is to design the VRM with very high-efficiency and high-power density to reduce the cost and size of the CPU/GPU motherboards. First, a two-stage power conversion structure will be used. The benefit of this structure is that it relies on existing technology using the 12V VRM for powering the CPU. The only modification required is the addition of another converter to step the 48V to the 12V level. This architecture can be easily adopted by industry, with only small modifications required on the system design level. Secondly, a single-stage power conversion structure is proposed that achieves higher efficiency and power density compared to the two-stage approach; however, the structure is very challenging to design and to meet all requirements by the CPU/GPU applications. All of these challenges will be addressed and solved in this work. The proposed architectures will be designed using an optimized magnetic structure. These structures achieve very high efficiency and power density in their designed architectures, compared to state-of-art solutions. In addition, they can be easily manufactured using automated manufacturing processes.
Chan, Yi-Tsu. "Design and Construction of Metallo-Supramolecular Terpyridine Architectures". University of Akron / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=akron1285698309.
Texto completoLiang, Heyi. "Rational Design of Soft Materials through Chemical Architectures". University of Akron / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=akron1573085345744325.
Texto completoTeodorov, Ciprian. "Model-driven physical design for future nanoscale architectures". Brest, 2011. http://www.theses.fr/2011BRES2050.
Texto completoIn the context where the traditional CMOS technology approaches its limits, some nanowire-based fabric proposals emerged, which all exhibit some common key characteristics. Among these, their bottom-up fabrication process leads to a regularity of assembly, which means the end of custom-made computational fabrics in favor of regular structures. Hence, research activities in this area, focus on structures conceptually similar to today’s reconfigurable PLA and/or FPGA architectures. A number of different fabrics and architectures are currently under investigation, e. G. CMOL , FPNI, NASIC. These proof-of-concept architectures take into account sortie fabrication constraints and support fault-tolerance techniques. What is still missing is the ability to capitalize on these experiments while offering a one-step shopping point for further research, especially at the physical-design level of the circuit design tool-flow. Sharing metrics, tools, and exploration capabilities is the next challenge to the nano-computing community. We address this problem by proposing a model-driven physical-design toolkit based on the factorization of common domain-specific concepts and the reification of the tool-flow. We used this tool-flow to drive the design-space exploration in the context of a novel nanoscale architecture, and we showed that such an approach assures design convergence based on frequent quantitative evaluations, moreover it enables incremental evolution of the architecture and the automation flow
Stonor, Andrew James. "The design of coinage metal and pnictogen architectures". Thesis, University of Bristol, 2015. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.683732.
Texto completoSun, Luo. "Design and process variation analysis of SRAM architectures". Thesis, University of Bristol, 2014. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.684909.
Texto completoLayton, Kent D. "Low-voltage analog CMOS architectures and design methods /". Diss., CLICK HERE for online access, 2007. http://contentdm.lib.byu.edu/ETD/image/etd2141.pdf.
Texto completoLayton, Kent Downing. "Low-Voltage Analog CMOS Architectures and Design Methods". BYU ScholarsArchive, 2007. https://scholarsarchive.byu.edu/etd/1218.
Texto completoBaroncini, Massimo <1979>. "Design, Synthesis and Characterization of new Supramolecular Architectures". Doctoral thesis, Alma Mater Studiorum - Università di Bologna, 2010. http://amsdottorato.unibo.it/2943/1/Baroncini_Massimo_Tesi.pdf.
Texto completoBaroncini, Massimo <1979>. "Design, Synthesis and Characterization of new Supramolecular Architectures". Doctoral thesis, Alma Mater Studiorum - Università di Bologna, 2010. http://amsdottorato.unibo.it/2943/.
Texto completoBOLLO, MATTEO. "Architectures and Design Methodologies for Micro and Nanocomputing". Doctoral thesis, Politecnico di Torino, 2017. http://hdl.handle.net/11583/2679368.
Texto completoCOCCIA, ARIANNA. "Design of Wideband Architectures for Modern Communication Standards". Doctoral thesis, Università degli studi di Pavia, 2019. http://hdl.handle.net/11571/1243908.
Texto completoRamaratnam, Rajiv. "An analysis of service oriented architectures". Thesis, Massachusetts Institute of Technology, 2007. http://hdl.handle.net/1721.1/42372.
Texto completoLeaf 96 blank.
Includes bibliographical references (leaves 88-95).
Introduction: Corporations all across the globe and of various sizes rely on their IT systems for business processes, reduction of process lifecycle and management of resources. These systems house several applications for internal sales, purchasing, finance, HR and so on. In any such typical organization, IT systems are a heterogeneous mix of hardware, operating systems and applications. Many of these applications run on different operating systems like Windows systems, Linux and Unix systems, etc. Oftentimes there is a need to consolidate data or access data from several such systems. The diversity among systems and applications makes these tasks difficult, time consuming and tedious. Furthermore, there is also a need for synchronization of data across systems and applications to ensure that the data is accurate and up-to-date. The heterogeneous nature of systems and applications lead to high levels of redundancy of data, making data maintenance a huge overhead for organizations. Today's organizations must also adapt to changes in environments both external and internal to them. Such changes could be changing market conditions, reorganization, change in business strategies within a company, addition or changing suppliers, partnerships, mergers and acquisitions and so on. There is also a growing need for integration across enterprise boundaries to facilitate fast and seamless collaboration between partners, customers and suppliers. All such needs entail changes to existing IT systems within an organization in a timely manner. There is thus a growing need for integration of such systems for consolidated decision making, accurate, up-to-date system information, better performance and system monitoring. IT Systems must also be flexible to respond to changes in the environments of their organization. Enterprise Application Integration is a process that aims to bring about such integration. The need for integration goes beyond the boundaries of an enterprise. Further, to successfully compete today, businesses need to be flexible. This means that their IT systems need to be able to keep pace with dynamic business conditions. It is evident that any solution for multiple IT systems to integrate with each other and to provide flexibility, they must be able to communicate and coordinate activities in a standard way. For almost two decades, many companies have tried to use CORBA, DCOM and similar technologies but have had little success. None of these technologies, for many reasons have become global technologies. The arrival of standards like HTTP and HTML helped linking together millions of humans across the internet but proved inadequate to link together computer systems. Moreover, internal and cross enterprise integration and coordination bring with them, security implications as both involve information exchange between organizational entities. As we will see later, the traditional methods of securing applications with firewalls prove inadequate for application security. One insight that has come from failed attempts to consolidate and coordinate IT systems is that such efforts cannot be limited to IT alone. Decision making on how interdepartmental and inter-enterprise data must data must be exchanged must be made by leaders and opinion shapers at each level or division of the organization. It is the goals of internal and external enterprise integration, flexibility of business processes, and enterprise data security that has led more and more organizations to adopt to Service Oriented Architectures (SOA). The adoption, implementation and running of a SOA does not simply involve IT department heads to design and create a new architecture for the enterprise. It involves a holistic understanding of the nature of the entire enterprise, its business and internal processes, the corporate strategy for the enterprise, an understanding of the business processes of the enterprise, its partners, suppliers, subsidiaries, etc. Such an undertaking is beyond the scope of a single department or division of the enterprise. The creation and running SOA architecture thus involves the coordination of all parts of the enterprise.
by Rajiv Ramaratnam.
S.M.
Zheng, Ning. "Discovering interpretable topics in free-style text diagnostics, rare topics, and topic supervision /". Columbus, Ohio : Ohio State University, 2008. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1199237529.
Texto completode, Tenorio Cyril. "Methods for collaborative conceptual design of aircraft power architectures". Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/34818.
Texto completoAlbarello, Nicolas. "Model-based trade studies in systems architectures design phases". Thesis, Châtenay-Malabry, Ecole centrale de Paris, 2012. http://www.theses.fr/2012ECAP0052/document.
Texto completoThe design of system architectures is a complex task which involves major stakes. During this activity, system designers must create design alternatives and compare them in order to select the most relevant system architecture given a set of criteria. In order to investigate different alternatives, designers must generally limit their trade studies to a small portion of the design-space which can be composed of a huge amount of solutions. Traditionally, the architecture design process is mainly driven by engineering judgment and designers' experiences and the selected alternatives are often adapted versions of known solutions. The risk is then to select a pertinent but yet under optimal solution. In order to increase the confidence in the optimality of the selected solution, the coverage of the design-space must be increased. The use of computational design synthesis methods proved to be an efficient way to support designers in the design of engineering artifacts (structures, electrical circuits...). In order to assist system designers during the architecture design process, a computational method for complex systems is defined. This method uses an evolutionary approach (genetic algorithms) to guide the design-space exploration process toward optimal zones. The initial population of the genetic algorithm is created thanks to a computational design synthesis technique which permits to create different physical architectures and allocation mappings for a given functional architecture. The method permits to obtain the optimal solutions of the stated design problem. These solutions can be then used by designers for more detailed trade studies or for technical negotiations with system suppliers
Allen, James D. "System level design issues for high performance SIMD architectures". Diss., Georgia Institute of Technology, 1996. http://hdl.handle.net/1853/15406.
Texto completoWilliams, Owen Ricardo. "Kinematics and design of robotic manipulators with complex architectures". Thesis, McGill University, 1989. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=61790.
Texto completoMorrow, Joseph M. (Joseph Monroe). "Design and analysis of lunar lander control system architectures". Thesis, Massachusetts Institute of Technology, 2012. http://hdl.handle.net/1721.1/76167.
Texto completoCataloged from PDF version of thesis.
Includes bibliographical references (p. 153-157).
Although a great deal of separate work exists on the development of spacecraft actuators and control algorithm design, less work exists which examines the connections between the selection of specific actuator types and placements, how this affects control algorithm design, and how these combined factors affect the overall vehicle performance of a lunar lander. This thesis attempts to address these issues by combining a functionality-oriented approach to actuator type/placement with a controls-oriented approach to algorithm design and performance analysis. Three example control system architectures are examined for a generic autonomous 350kg lunar lander during the terminal descent flight phase. Results indicate that stability and control can be achieved using a wide variety of actuator types/placements and algorithms given that a set of 'common sense' subsystem functionality and robustness metrics are met; however, algorithm development was often heavily influenced/restricted by actuator system capabilities. It is therefore recommended that future designers of lunar lander vehicles consider the impact of their control system architectures from both a functionality-oriented and a controls-oriented approach to gain a more complete understanding of the effects of their choices on overall performance.
by Joseph M. Morrow.
S.M.
Krieger, James David 1978. "Architectures and system design for digitally-enhanced antenna arrays". Thesis, Massachusetts Institute of Technology, 2014. http://hdl.handle.net/1721.1/87925.
Texto completoCataloged from PDF version of thesis.
Includes bibliographical references (pages 143-147).
Digital techniques have had longstanding use in both the operational control and signal processing efforts associated with phased array antennas. Fundamentally, these techniques have served to provide additional levels of convenience and performance over the fully analog counterparts, without specifically addressing the underlying design of the analog hardware aspects of the arrays. The class of digitally-enhanced hardware has recently emerged, wherein "digitally aware" design approaches are used for the purpose of alleviating the high cost and complexity of sophisticated analog devices. Emergent trends in millimeter wave and low-terahertz circuit technology are enabling the prospect of physically small, yet electrically large antenna arrays for a host of exciting new communication, radar, and imaging applications. Still, the high cost of phased arrays remains a significant bottleneck to any widespread deployment in this regard. In light of this challenge, we propose two phased array architectures for which the notion of digital awareness plays a central role in their designs. The Dense Delta-Sigma Array: Primarily motivated by advancements in low-cost fabrication, this design concept provides the opportunity to replace the expensive RF components required to control the individual array element excitations with inexpensive phase shifter components having particularly coarse resolution (as few as 2-bits). This is made possible by increasing the number of array elements for a given aperture beyond the nominal number associated with the standard half-wavelength spacing. This approach is inspired by Delta-Sigma data converters, which employ faster-than-Nyquist sampling with low quantization resolution. The Sparse Multi-Coset Array: This design concept exploits the sparsity commonly found in typical environments to allow for target detection and imaging with significantly fewer array elements than prescribed by conventional half-wavelength spacing. The result is a structured periodic non-uniform array composed of a number of distinct subarrays known as cosets. This approach is inspired by multi-coset sampling, for which the average sampling rate may be reduced below the Nyquist convention when the spectral components within the overall bandwidth are limited to some number of sub-bands. In this approach, we view the underlying engineering design problem as one of compressive sensing. In this thesis, we develop and apply the underlying mathematical principles and concepts of the dense and sparse arrays, taking into account the practical constraints and issues that make the system design, analysis, and performance evaluation rich from an engineering perspective.
by James David Stone Krieger.
Ph. D.
Ludlow, James M. III. "Design and Synthesis of Terpyridine based Metallo-Supramolecular Architectures". University of Akron / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=akron1444989836.
Texto completoKurland, Nicholas. "Design of Engineered Biomaterial Architectures Through Natural Silk Proteins". VCU Scholars Compass, 2013. http://scholarscompass.vcu.edu/etd/571.
Texto completoLahiri, Kanishka. "On-chip communication : system-level architectures and design methodologies /". Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2003. http://wwwlib.umi.com/cr/ucsd/fullcit?p3091346.
Texto completoAncajas, Dean Michael B. "Design of Reliable and Secure Network-On-Chip Architectures". DigitalCommons@USU, 2015. https://digitalcommons.usu.edu/etd/4150.
Texto completoHo, Phuong Minh. "Parallel architectures for solving combinatorial problems of logic design". PDXScholar, 1989. https://pdxscholar.library.pdx.edu/open_access_etds/3872.
Texto completoWu, Ziyang. "Rational design of two-dimensional architectures for efficient electrocatalysis". Thesis, Queensland University of Technology, 2022. https://eprints.qut.edu.au/235888/1/ziyang%2Bwu%2Bthesis%284%29.pdf.
Texto completoWalker, Simon N. "High speed algorithms and architectures for RSA encryption". Thesis, University of Sheffield, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.298054.
Texto completoLaFon, Christian (Christian Phillip). "Context characterization for synthesis of process architectures". Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/47871.
Texto completoIncludes bibliographical references (leaves 115-118).
Analysis steps are proposed as an aid for establishing Lean Product Development (LPD) activities in an organization. The proposal is offered as an aid to engineering managers and process designers for coping with the unique challenges of implementing processes from their inception - for example, at a new enterprise. As such, the thesis focuses on the creation of LPD, as opposed to traditional Lean improvement activities which benefit from the perspective of hindsight of a legacy process. Without established product development processes to improve upon, the implementation of product development activities at a new venture relies on the use of foresight to instance a LPD environment in new organizations. Therefore, the paper stresses stakeholder value delivery within the specific context that an enterprise operates and competes. A generic framework for context characterization is proposed and discussed. The framework is then evaluated for its usefulness in process design activities. The analysis steps are based on literature review and case study interviews. The proposed analysis steps include: * a comprehensive definition of the business context in which the enterprise operates and competes, * a statement of goals and objectives for the product development organization based on this context, and, * a determination of appropriate behaviors to meet these goals. Traditional Lean research has typically been approached from a large-scale, complex systems, for-profit perspective.
(cont.) Unique insights are gained from the perspective of small, privately funded, new ventures. The benefits include foresight-only value objectives for product development (process creation) and uniqueness of context (i.e. resource limited, mindshare-driven). The analysis method was validated by examining process design case studies within three contexts: large-scale aerospace, industrial process monitoring, and high-technology start-up.
by Christian LaFon.
S.M.
Sekar, Krishna. "Dynamically configurable system-on-chip platforms architectures and design methodologies /". Diss., Connected to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2005. http://wwwlib.umi.com/cr/ucsd/fullcit?p3190004.
Texto completoTitle from first page of PDF file (viewed March 8, 2006). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 151-165).
Altinigneli, Muzaffer Can. "Pipelined Design Approach To Microprocessor Architectures A Partial Implementation: Mips". Master's thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/12606778/index.pdf.
Texto completoNarayanan, Sridhar. "Formal methods for reuse of design patterns and micro-architectures". Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/mq26018.pdf.
Texto completoPayan, Alexia Paule Marie-Renee. "Enabling methods for the design and optimization of detection architectures". Diss., Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/47688.
Texto completoBanz, Christian [Verfasser]. "Design and Analysis of Architectures for Stereo Vision / Christian Banz". Aachen : Shaker, 2013. http://d-nb.info/1048457915/34.
Texto completo