FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891806687> ?p ?o ?g. }

• W2891806687 abstract "Author(s): Darvish Rouhani, Bita | Advisor(s): Koushanfar, Farinaz | Abstract: Contemporary datasets are rapidly growing in size and complexity. This wealth of data is providing a paradigm shift in various key sectors including defense, commercial, and personalized computing. Over the past decade, machine learning and related fields have made significant progress in designing rigorous algorithms with the goal of making sense of this large corpus of available data. Concerns over physical performance (runtime and energy consumption), reliability (safety), and ease-of-use, however, pose major roadblocks to the wider adoption of machine learning techniques. To address the aforementioned roadblocks, a popular recent line of research is focused on performance optimization and machine learning acceleration via hardware/software co-design and automation. This thesis advances the state-of-the-art in this growing field by advocating a holistic automated co-design approach which involves not only hardware and software but also the geometry of the data and learning model as well as the security requirements. My key contributions include: Co-optimizing graph traversal, data embedding, and resource allocation for succinct training and execution of Deep Learning (DL) models. The resource efficiency of my end-to-end automated solutions not only enables compact DL training/execution on edge devices but also facilitates further reduction of the training time and energy spent on cloud data servers. Characterizing and thwarting adversarial subspace for robust and assured execution of DL models. I build a holistic hardware/software/algorithm co-design that enables just-in-time defense against adversarial attacks. My proposed countermeasure is robust against the strongest adversarial attacks known to date without violating the real-time response requirement, which is crucial in sensitive applications such as autonomous vehicles/drones. Proposing the first efficient resource management framework that empowers coherent integration of robust digital watermarks/fingerprints into DL models. The embedded digital watermarks/fingerprints are robust to removal and transformation attacks and can be used for model protection against intellectual property infringement. Devising the first reconfigurable and provably-secure framework that simultaneously enables accurate and scalable DL execution on encrypted data. The proposed framework supports secure streaming-based DL computation on cloud servers equipped with FPGAs. Developing the first scalable framework that enables real-time approximation of multi-dimensional probability density functions for causal Bayesian analysis. The proposed solution adaptively fine-tunes the underlying latent variables to cope with the data dynamics as it evolves over time." @default.
• W2891806687 created "2018-09-27" @default.
• W2891806687 creator A5035073741 @default.
• W2891806687 date "2018-08-01" @default.
• W2891806687 modified "2023-09-27" @default.
• W2891806687 title "Succinct and Assured Machine Learning: Training and Execution" @default.
• W2891806687 hasPublicationYear "2018" @default.
• W2891806687 type Work @default.
• W2891806687 sameAs 2891806687 @default.
• W2891806687 citedByCount "0" @default.
• W2891806687 crossrefType "dissertation" @default.
• W2891806687 hasAuthorship W2891806687A5035073741 @default.
• W2891806687 hasConcept C108583219 @default.
• W2891806687 hasConcept C111919701 @default.
• W2891806687 hasConcept C119857082 @default.
• W2891806687 hasConcept C120314980 @default.
• W2891806687 hasConcept C154945302 @default.
• W2891806687 hasConcept C2522767166 @default.
• W2891806687 hasConcept C26517878 @default.
• W2891806687 hasConcept C2777904410 @default.
• W2891806687 hasConcept C37736160 @default.
• W2891806687 hasConcept C38652104 @default.
• W2891806687 hasConcept C41008148 @default.
• W2891806687 hasConceptScore W2891806687C108583219 @default.
• W2891806687 hasConceptScore W2891806687C111919701 @default.
• W2891806687 hasConceptScore W2891806687C119857082 @default.
• W2891806687 hasConceptScore W2891806687C120314980 @default.
• W2891806687 hasConceptScore W2891806687C154945302 @default.
• W2891806687 hasConceptScore W2891806687C2522767166 @default.
• W2891806687 hasConceptScore W2891806687C26517878 @default.
• W2891806687 hasConceptScore W2891806687C2777904410 @default.
• W2891806687 hasConceptScore W2891806687C37736160 @default.
• W2891806687 hasConceptScore W2891806687C38652104 @default.
• W2891806687 hasConceptScore W2891806687C41008148 @default.
• W2891806687 hasLocation W28918066871 @default.
• W2891806687 hasOpenAccess W2891806687 @default.
• W2891806687 hasPrimaryLocation W28918066871 @default.
• W2891806687 hasRelatedWork W1849043681 @default.
• W2891806687 hasRelatedWork W2028352624 @default.
• W2891806687 hasRelatedWork W2148073520 @default.
• W2891806687 hasRelatedWork W2223315718 @default.
• W2891806687 hasRelatedWork W2497767505 @default.
• W2891806687 hasRelatedWork W2626822961 @default.
• W2891806687 hasRelatedWork W2755454882 @default.
• W2891806687 hasRelatedWork W2782797544 @default.
• W2891806687 hasRelatedWork W2783144021 @default.
• W2891806687 hasRelatedWork W2806773351 @default.
• W2891806687 hasRelatedWork W2807596110 @default.
• W2891806687 hasRelatedWork W2889776294 @default.
• W2891806687 hasRelatedWork W2942616794 @default.
• W2891806687 hasRelatedWork W3015313343 @default.
• W2891806687 hasRelatedWork W3033807643 @default.
• W2891806687 hasRelatedWork W3092150361 @default.
• W2891806687 hasRelatedWork W3115916398 @default.
• W2891806687 hasRelatedWork W3134778422 @default.
• W2891806687 hasRelatedWork W3134848794 @default.
• W2891806687 hasRelatedWork W3153692005 @default.
• W2891806687 isParatext "false" @default.
• W2891806687 isRetracted "false" @default.
• W2891806687 magId "2891806687" @default.
• W2891806687 workType "dissertation" @default.