Sökning: "quantization"
Visar resultat 1 - 5 av 138 uppsatser innehållade ordet quantization.
1. 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)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
2. Detecting Distracted Drivers using a Federated Computer Vision Model : With the Help of Federated Learning
Kandidat-uppsats, Mittuniversitetet/Institutionen för data- och elektroteknik (2023-)Sammanfattning : En av de vanligaste distraktionerna under bilkörning är utförandet av aktiviteter som avlägsnar förarens fokus från vägen, exempelvis användandet av en telefon för att skicka meddelanden. Det finns många olika sätt att hantera dessa problem, varav en teknik är att använda maskininlärning för att identifiera och notifiera distraherade bilförare. LÄS MER
3. Methods for Developing TinyConvolutional Neural Networksfor Deployment on EmbeddedSystems
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : 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
4. Design of a grating lobe mitigated antenna array architecture integrated with low loss PCB filtering structures
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Massive multiple input multiple output - MIMO systems are a reality and modern communication systems rely upon this technology to cope with the increasing need for capacity and network usage. Antenna arrays are at the heart of the of the massive-MIMO system and are the enabling technology. LÄS MER
5. 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)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