Suchergebnisse - "Computer Learning AND Pattern Recognition::Uncertainity Management"

Thermodynamics behavior prediction of nickel alloys at elevated temperatures with artificial intelligence ; Yapay zeka ile yüksek sıcaklıktaki nikel alaşımları için termodinamik davranışın tahmini

Autoren: Dinçer, Mehmet Şamil Sargın, Irmak Department of Metallurgical and Materials Engineering

Weitere Verfasser: Dinçer, Mehmet Şamil Sargın, Irmak Department of Metallurgical and Materials Engineering

Schlagwörter: Bayesian Neural Network (BNN), Calculation of Phase Diagram (CALPHAD), High Throughput Calculation (HTC), Nickel-Based Superalloys, Arbis Subjects::Engineering and Technology::Metallurgical and Materials Engineering::Material science and engineering::Metallic Materials, Arbis Subjects::Engineering and Technology::Metallurgical and Materials Engineering::Other, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition::Computer Learning, Computer Learning and Pattern Recognition::Neural Networks, Computer Learning and Pattern Recognition::Uncertainity Management

Dateibeschreibung: 77 pages; application/pdf

Relation: https://hdl.handle.net/11511/116631

Verfügbarkeit: https://hdl.handle.net/11511/116631

ENHANCING DNN TEST DATA SELECTION THROUGH UNCERTAINTY-BASED AND DATA DISTRIBUTION-AWARE APPROACHES ; BELİRSİZLİĞE DAYALI VE VERİ DAĞILIMINA DUYARLI YAKLAŞIMLAR YOLUYLA DNN TESTI VERİ SEÇİMİNİN GELİŞTİRİLMESİ

Autoren: Demir, Demet Sürer, Elif Betin Can, Aysu et al.

Weitere Verfasser: Demir, Demet Sürer, Elif Betin Can, Aysu et al.

Schlagwörter: Deep Neural Network Testing, Test Data Selection and Prioritization, Data Distribution, Deep Learning Explainability, Deep Learning Uncertainty, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition::Neural Networks, Computer Learning and Pattern Recognition::Uncertainity Management, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision::Computer Vision, Arbis Subjects::Engineering and Technology::Computer Sciences::Software::Software Engineering

Dateibeschreibung: application/pdf

Relation: https://hdl.handle.net/11511/110146

Verfügbarkeit: https://hdl.handle.net/11511/110146

DynapSIM: A Fast, Optimizable, and Mismatch Aware Mixed-Signal Neuromorphic Chip Simulator ; DynapSIM: Hızlı, Optimize Edilebilir ve Uyuşmazlık Duyarlı Karma Sinyalli Nöromorfik Çip Simülatörü

Autoren: Çakal, Uğurcan Ulusoy, İlkay Muir, Dylan Richard et al.

Weitere Verfasser: Çakal, Uğurcan Ulusoy, İlkay Muir, Dylan Richard et al.

Schlagwörter: Mixed-Signal, Chip Simulation, Dynap-SE1, Dynap-SE2, Neuromorphic Computing, Neuromorphic Hardware, Non-Von-Neumann Computing, Silicon Brain, Spiking Neural Networks, Arbis Subjects::Engineering and Technology::Computer Sciences::Algorithms::Computational Model, Arbis Subjects::Engineering and Technology::Computer Sciences::Algorithms::Simulation and Modelling, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition::Computer Learning, Computer Learning and Pattern Recognition::Neural Networks, Computer Learning and Pattern Recognition::Uncertainity Management, Arbis Subjects::Natural Sciences::Life Sciences::Neurobiology::Numerical Neuroscience, Arbis Subjects::Engineering and Technology::Computer Sciences::Equipment::Application Based Architecture, Arbis Subjects::Engineering and Technology::Computer Sciences::Equipment::Integrated Circuits, Arbis Subjects::Engineering and Technology::Computer Sciences::Equipment::Network Architecture, Arbis Subjects::Engineering and Technology::Computer Sciences::Equipment::Processor Architectures, Arbis Subjects::Engineering and Technology::Electrical and Electronics Engineering::Electronic::Electronic Circuits

Dateibeschreibung: 132 pages; application/pdf

Relation: https://hdl.handle.net/11511/98616

Verfügbarkeit: https://hdl.handle.net/11511/98616

Feature enhancement with deep generative models in deep bayesian active learning ; Bayes derin aktif öğrenmede derin üretici modeller ile öznitelik iyileştirme

Autoren: Duymuş, Pınar Ezgi Ertekin Bolelli, Şeyda Department of Computer Engineering

Weitere Verfasser: Duymuş, Pınar Ezgi Ertekin Bolelli, Şeyda Department of Computer Engineering

Schlagwörter: Bayesian active learning, Deep generative models, Feature learning, Latent space representation, Mode-collapse problem, Arbis Subjects::Natural Sciences::Statistics::Statistical Analysis and Applications, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition::Uncertainity Management, Computer Learning and Pattern Recognition::Neural Networks

Dateibeschreibung: 66 pages; application/pdf

Relation: https://hdl.handle.net/11511/99446

Verfügbarkeit: https://hdl.handle.net/11511/99446

Towards Uncertainty-Aware Disentangled Representations ; Belirsizliğe Duyarlı Dolaşıklığı Açılmış Temsillere Doğru

Autoren: Özyeğin, Sezai Artun Kalkan, Sinan Department of Computer Engineering

Weitere Verfasser: Özyeğin, Sezai Artun Kalkan, Sinan Department of Computer Engineering

Schlagwörter: Disentanglement, Uncertainty Estimation, Representation Learning, Deep Learning, Arbis Subjects::Engineering and Technology::Computer Sciences::Artificial Intelligence, Computer Learning and Pattern Recognition::Uncertainity Management, Computer Learning and Pattern Recognition::Neural Networks, Computer Learning and Pattern Recognition::Computer Learning, Arbis Subjects::Engineering and Technology::Computer Sciences::Computer Vision

Dateibeschreibung: application/pdf

Relation: https://hdl.handle.net/11511/93206

Verfügbarkeit: https://hdl.handle.net/11511/93206