Global ETD Search

Dirbtinio intelekto panaudojimo tyrimas baltymų analizei /

Kuklys, Domantas,Institutional Repository of Vilnius University2024

… work is to investigate the potential of deep neural networks for structural element recognition in large structures, choosing the LH1-RC complex for analysis. The main objectives of this work are: to investigate the applicability of deep, fully connected neural networks for two and three …

vilnius Repository record for Dirbtinio intelekto panaudojimo tyrimas baltymų analizei / (opens in a new tab)

A Full System Co-Simulation Platform for Evaluating Edge Machine Learning Inference Using Compute-in-Memory

Lee, Belsen

… MNIST image inference workload and a synthetic fully connected neural network, comparing CPU-only execution with CIM-offloaded execution. For MNIST, CIM reduces CPU instruction count by 88.6% and estimated total system dynamic energy by 84.0%. Furthermore, stress-testing with the large synthetic …

chapman Repository record for A Full System Co-Simulation Platform for Evaluating Edge Machine Learning Inference Using Compute-in-Memory (opens in a new tab)

Performance evaluation of text augmentation methods with BERT on imbalanced datasets

Hu, LingshuUniversity of Missouri--Columbia2022

… learning models, including logistic regression, fully connected neural network, and LSTM. Experimental results show that Word2Vec augmentation improves the performance of BERT in detecting the minority class, and the improvement is most significantly (9 percent-30 percent recall increase compared …

missouri Repository record for Performance evaluation of text augmentation methods with BERT on imbalanced datasets (opens in a new tab)

Building Inventory Simulations for High Velocity Garment Retail Stores

Qi, DavyMassachusetts Institute of Technology2024

… the efficacy of linear regression, tree and fully connected neural network models at making time series predictions using two time series as inputs. It also rigorously dives into the limitations and advantages of various model architectures, including the selection of variables, treatment of …

mit Repository record for Building Inventory Simulations for High Velocity Garment Retail Stores (opens in a new tab)

Human action recognition with 3D convolutional neural networks

Cronje, FransDepartment of Statistical Sciences2015

Convolutional neural networks (CNNs) adapt the regular fully-connected neural network (NN) algorithm to facilitate image classification. Recently, CNNs have been demonstrated to provide superior performance across numerous image classification databases including large natural images (Krizhevsky et …

cape-town Repository record for Human action recognition with 3D convolutional neural networks (opens in a new tab)

Multiscale forward and inverse problems with the DGFD method and the deep learning method

Zhang, Runren2020

… </p><p>For the inversion part, a convolutional neural network based inversion has been developed to reconstruct the lateral extent and direction of the hydraulic fracture through scattered electromagnetic field data under borehole-to-surface measurements; further, the deep transfer learning is …

duke Repository record for Multiscale forward and inverse problems with the DGFD method and the deep learning method (opens in a new tab)

SOC Reconfigurable Architecture for Software-Trained Neural Networks on FPGA

Wasef, Michael

boise Repository record for SOC Reconfigurable Architecture for Software-Trained Neural Networks on FPGA (opens in a new tab)

AI-based leakage prediction with uncertainty quantification and explainable AI for nuclear system

Abusultan, AhmedUniversity of Illinois Urbana-Champaign2025

Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01

uiuc Repository record for AI-based leakage prediction with uncertainty quantification and explainable AI for nuclear system (opens in a new tab)