Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 32 for “"Accuracy cost"”.

  1. Stochastic m-estimators: controlling accuracy-cost tradeoffs in machine learning

    … physical resources for desired levels of accuracy. These limiting factors, which we abstractly refer as costs, may be computational, such as time-limited cluster access for parameter learning, or they may be financial, such as purchasing human-labeled training data under a fixed budget. …

    gatech Repository record for Stochastic m-estimators: controlling accuracy-cost tradeoffs in machine learning (opens in a new tab)

  2. Accuracy, Cost and Performance Trade-Offs for Streaming Set-Wise Floating Point Accumulation on FPGAs

    … In these applications, maintaining the accuracy of the summation is also important as floating point operations have inherent errors associated with them. Designing floating-point accumulators presents a unique set of challenges: double-precision addition is usually deeply pipelined and …

    south-carolina Repository record for Accuracy, Cost and Performance Trade-Offs for Streaming Set-Wise Floating Point Accumulation on FPGAs (opens in a new tab)

  3. Minimizing Run Time of Finite Element Analyses: Applications in Conformable CNG Tank Modeling

    … to reduce model run time without reducing accuracy. Methods covered include creating symmetric building blocks, gradient meshing, and hybrid (shell to solid) meshing. Results indicate that building block and gradient methods reduce run time by 84% and 78% respectively for an accuracy cost …

    mtu Repository record for Minimizing Run Time of Finite Element Analyses: Applications in Conformable CNG Tank Modeling (opens in a new tab)

  4. Latency-aware depth pruning and when block selection matters

    … can lose many blocks and regain most of their accuracy through fine-tuning, so depth pruning cuts latency. This thesis presents a depth-pruning method and a benchmark asking when block selection matters. The method, LAG-Net, trains a gate for each residual block with the weights, then fixes the …

    uoit Repository record for Latency-aware depth pruning and when block selection matters (opens in a new tab)

  5. Daugiaagentė sistema, naudojanti didelės kalbos modelius verslo procesams automatizuoti /

    … only half of the output tokens. Smaller models’ accuracy is increased by 0,16‑0,18 adding OCR, reasoning add no additional value, and parallel processing increases throughput up to 60 % without accuracy cost. Total cost of the experiment was ≈4.63 EUR, 20 to 540 times cheaper than the same …

    vilnius Repository record for Daugiaagentė sistema, naudojanti didelės kalbos modelius verslo procesams automatizuoti / (opens in a new tab)

  6. An Integrated Camera and Radar on-Robot System for Human Robot Collaboration

    … robot workspace. The challenge is to balance the accuracy, cost, and responsiveness of the system to maximize the safety of the worker. This work presents a sensor system that combines six 60GHz radar modules and six cameras to accurately track the location and speed of the workers in all 360 …

    rit Repository record for An Integrated Camera and Radar on-Robot System for Human Robot Collaboration (opens in a new tab)

  7. Mirror Rehabilitation Therapy with Mirrored Glove

    … was selected for its optimal balance of accuracy, cost, and reliability. The motorized glove utilizes servo motors and a tendon-pulley system anchored with custom silicone rings to replicate finger flexion. The device demonstrated accurate motion replication, comfort, and strong potential …

    unt Repository record for Mirror Rehabilitation Therapy with Mirrored Glove (opens in a new tab)

  8. Deep Learning and Adaptive Clustering Approaches for Flood Prediction and Efficient Sensor Placement in Missouri

    … models, with the main objective of improving the accuracy of flood predictions and sensor placement. Four distinct deep learning models are used to forecast water levels for a designated set of gage stations in Missouri. The comparative analysis assesses the effectiveness of four deep learning …

    must-thes Repository record for Deep Learning and Adaptive Clustering Approaches for Flood Prediction and Efficient Sensor Placement in Missouri (opens in a new tab)

  9. Enabling Multi-Task Neural Network Inference on Heterogeneous Edge Devices

    … a network acquire without incurring deployment cost? The first study takes an ImageNet-pretrained ResNet-18, sweeps the branch point across every residual stage and the classification-head depth across one, ten, and twenty layers, and deploys the resulting multi-head model to an NVIDIA Jetson …

    kennesaw Repository record for Enabling Multi-Task Neural Network Inference on Heterogeneous Edge Devices (opens in a new tab)

  10. Data-Driven Decision-Making Under Uncertainty: An Empirical Study of U.S. Wildfire Management

    … management in the United States faces prediction accuracy, cost efficiency, and fiscal sustainability issues. This dissertation integrates three interrelated research topics to develop integrated decision models applicable to each stage of wildfire management. The first study evaluates the role of …

    waterloo Repository record for Data-Driven Decision-Making Under Uncertainty: An Empirical Study of U.S. Wildfire Management (opens in a new tab)

  11. Performance of minimum quantity cooling (MQC) when turning aluminum alloy 6061-T6 : surface roughness, tool temperature and aerosol emission

    … industries desire to obtain parts with better accuracy (dimensional and form) and surface finish at low cost. These factors (accuracy, cost and productivity) are used to evaluate the performance of machining processes. When material removal rate increases, the higher tool temperature is …

    ets-quebec Download PDF for Performance of minimum quantity cooling (MQC) when turning aluminum alloy 6061-T6 : surface roughness, tool temperature and aerosol emission (opens in a new tab)

  12. Evaluating the Value of Information Concerning Different Methods of Forest Sampling

    … However, the compromise made between the cost of sampling methods during inventory, and the accuracy of the information gathered has not been fully recognized. This study evaluates the value of information across multiple sampling methods and intensities. The objectives focus on 1) …

    vt Repository record for Evaluating the Value of Information Concerning Different Methods of Forest Sampling (opens in a new tab)

  13. The design and validation of ultrasound-augmented self-localizing tools for dynamic and adjustable registration and navigation in spinal surgery

    … and robotic systems—offer varying degrees of accuracy but are constrained by challenges such as high costs, radiation exposure, and workflow disruptions. To address these limitations, this thesis proposes and evaluates an innovative, ultrasound-augmented, self-localizing drill guide that …

    ubc Repository record for The design and validation of ultrasound-augmented self-localizing tools for dynamic and adjustable registration and navigation in spinal surgery (opens in a new tab) Download PDF for The design and validation of ultrasound-augmented self-localizing tools for dynamic and adjustable registration and navigation in spinal surgery (opens in a new tab)

  14. Designing optimal object detection networks for detecting damages to canola kernels

    … networks was to mitigate trade-offs among speed, accuracy, cost, and model size, thereby creating a more balanced and optimized network. Several architectural design options were explored to compress the network structure of the two models in terms of size and cost yet retain or improve the …

    manitoba Repository record for Designing optimal object detection networks for detecting damages to canola kernels (opens in a new tab)

  15. Monitoring-as-a-service in the cloud

    … quality and performance parameters, such as accuracy, cost, scalability and customizability. This dissertation research is dedicated to innovative research and development of an elastic framework for providing state monitoring as a service (MaaS). We analyze limitations of existing …

    gatech Repository record for Monitoring-as-a-service in the cloud (opens in a new tab)

  16. A non-contact video-oculograph for tracking gaze in a human computer interface

    … interface. However, issues such as speed, accuracy, cost and case of use have so far limited the widespread, practical application of existing devices. No pre-existing device that does not require user contact is able to accurately track the eye (and hence where a person is looking) in real …

    ubc Repository record for A non-contact video-oculograph for tracking gaze in a human computer interface (opens in a new tab) Download PDF for A non-contact video-oculograph for tracking gaze in a human computer interface (opens in a new tab)

  17. An exploration of the utility of augmented haptic feedback for learning a curve-tracing task

    … measure of performance efficiency (the speed accuracy cost function) on retention tests conducted immediately (10 min) and 1 day after skill acquisition. Results showed that error-augmenting haptic feedback was the most effective for learning (study 1) but its superiority was not observed with …

    toronto-retro Repository record for An exploration of the utility of augmented haptic feedback for learning a curve-tracing task (opens in a new tab)

  18. Near-Memory Computing Architectures for Scalable Edge AI Applications

    … and memory continues to dominate system cost. Thesetrends position memory-centric computing as a compelling alternative to conventional architectures.Addressing these challenges begins with rethinking on-chip memory. A dual-port six-transistor (6T) static random-accessmemory (SRAM) was …

    lund Repository record for Near-Memory Computing Architectures for Scalable Edge AI Applications (opens in a new tab) Download PDF for Near-Memory Computing Architectures for Scalable Edge AI Applications (opens in a new tab)

  19. Sampling Strategy and Accuracy Assessment for Digital Terrain Modelling

    … related to three of the main concerns (i. e. accuracy, cost and efficiency) of digital terrain modelling have been carried out. Special attention has been given to two main issues - the establishment of a family of mathematical models which is comprehensive in theory and reliable in practice, …

    glasgow Download PDF for Sampling Strategy and Accuracy Assessment for Digital Terrain Modelling (opens in a new tab)

  20. MEAT QUALITY PREDICTION USING MACHINE LEARNING

    … quality prediction have limitations in terms of accuracy, cost, and time efficiency. This project focused on utilizing advanced Deep learning and Machine learning algorithms to develop- machine learning models that could predict the freshness (or spoilage) of meat with a 100% accuracy, based on …

    csusb Repository record for MEAT QUALITY PREDICTION USING MACHINE LEARNING (opens in a new tab)

Page 1 of 2