Sökning: "network pruning"
Visar resultat 1 - 5 av 23 uppsatser innehållade orden network pruning.
1. Exploring the Depth-Performance Trade-Off : Applying Torch Pruning to YOLOv8 Models for Semantic Segmentation Tasks
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In order to comprehend the environments from different aspects, a large variety of computer vision methods are developed to detect objects, classify objects or even segment them semantically. Semantic segmentation is growing in significance due to its broad applications in fields such as robotics, environmental understanding for virtual or augmented reality, and autonomous driving. LÄS MER
2. The Impact of Deep Neural Network Pruning on the Hyperparameter Performance Space: An Empirical Study
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : With the continued growth of deep learning models in terms of size and computational requirements, the need for efficient models for deployment on resource-constrained devices becomes crucial. Structured pruning has emerged as a proven method to speed up models and reduce computational requirements. LÄS MER
3. What happens in the brain during adolescence? : A systematic review of gray and white matter changes during adolescence
Kandidat-uppsats, Högskolan i Skövde/Institutionen för biovetenskapSammanfattning : During adolescence, the brain undergoes significant reorganization due to myelination and synaptic pruning. These changes are associated with risk-taking behaviors and the development of social relationships. Recent advancements in adolescent brain development can potentially enhance strategies for preventing and treating mental health disorders. LÄS MER
4. On GPU Assisted Polar Decoding : Evaluating the Parallelization of the Successive Cancellation Algorithmusing Graphics Processing Units
Master-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)Sammanfattning : In telecommunication, messages sent through a wireless medium often experience noise interfering with the signal in a way that corrupts the messages. As the demand for high throughput in the mobile network is increasing, algorithms that can detectand correct these corrupted messages quickly and accurately are of interest to the industry. LÄS MER
5. Compressing Deep Learning models for Natural Language Understanding
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Uppgifter för behandling av naturliga språk (NLP) har under de senaste åren visat sig vara särskilt effektiva när man använder förtränade språkmodeller som BERT. Det enorma kravet på datorresurser som krävs för att träna sådana modeller gör det dock svårt att använda dem i verkligheten. LÄS MER