Sökning: "quantized"

Visar resultat 1 - 5 av 53 uppsatser innehållade ordet quantized.

1. 1. Using Synthetic Data For Object Detection on the edge in Hazardous Environments

   Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknik

   Författare :Faraz Azarnoush; Damil Sabotic; [2024]
   Nyckelord :Technology and Engineering;

   Sammanfattning : This thesis aims to evaluate which aspects are important when generating synthetic data with the purpose of running on a lightweight object detection model on an edge device. The task we constructed was to detect Canisters and whether they feature a protective valve called a Cap or not (called a No-Cap). LÄS MER

3. 2. Utilizing energy-saving techniques to reduce energy and memory consumption when training machine learning models : Sustainable Machine Learning

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Khalid El Yaacoub; [2024]
   Nyckelord :Sustainable AI; Machine learning; Quantization-Aware Training; Model Distillation; Quantized Distillation; Siamese Neural Networks; Continual Learning; Experience Replay; Data Efficient AI; Energy Consumption; Energy-Savings; Sustainable ML; Computation resources; Hållbar maskin inlärning; Hållbar AI; Maskininlärning; Quantization-Aware Training; Model Distillation; Quantized Distillation; siamesiska neurala nätverk; Continual Learning; Experience Replay; Dataeffektiv AI; Energiförbrukning; Energibesparingar; Beräkningsresurser;

   Sammanfattning : Emerging machine learning (ML) techniques are showing great potential in prediction performance. However, research and development is often conducted in an environment with extensive computational resources and blinded by prediction performance. LÄS MER

4. 3. Methods for Developing TinyConvolutional Neural Networksfor Deployment on EmbeddedSystems

   Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Egemen Yiğit Kömürcü; [2023]
   Nyckelord :;

   Sammanfattning : With the recent development in the Deep Learning area, computationally heavy tasks like object detection in images have become easier to compute and take less time to execute with powerful GPUs. Also, when employing sufficiently larger models, these daily tasks are predicted with greater accuracy. LÄS MER

5. 4. Enhancing Long-Term Human Motion Forecasting using Quantization-based Modelling. : Integrating Attention and Correlation for 3D Motion Prediction

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Luis González Gudiño; [2023]
   Nyckelord :Human Motion Forecasting; Long-Term Prediction; VQ-VAE; Quantization; 3D Human Motion; CMU MoCap Dataset; Transformer; Mänsklig Rörelseprognos; Långsiktig Prognos; VQ-VAE; Kvantisering; 3D-mänsklig rörelse; CMU MoCap Dataset; Transformer;

   Sammanfattning : This thesis focuses on addressing the limitations of existing human motion prediction models by extending the prediction horizon to very long-term forecasts. The objective is to develop a model that achieves one of the best stable prediction horizons in the field, providing accurate predictions without significant error increase over time. LÄS MER

7. 5. Implementing a Network Optimized Federated Learning Method From the Ground up

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Gustav Källander; Henning Norén; [2023]
   Nyckelord :;

   Sammanfattning : This bachelor thesis presents the implementation ofa simple fully connected neural network (FCNN) and federatedneural network with stochastic quantization from scratch andcompares their performance. Federated learning enables multipleparties to contribute to a machine learning model withoutsharing their sensitive data. LÄS MER