Advanced search
Showing result 1 - 5 of 50 essays matching the above criteria.
-
1. Understanding the Robustnessof Self Supervised Representations
University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknikAbstract : This work investigates the robustness of learned representations of self-supervised learn-ing approaches, focusing on distribution shifts in computer vision. Joint embedding architecture and method-based self-supervised learning approaches have shown advancesin learning representations in a label-free manner and efficient knowledge transfer towardreducing human annotation needs. READ MORE
-
2. Comparative Study of the Inference of an Image Quality Assessment Algorithm : Inference Benchmarking of an Image Quality Assessment Algorithm hosted on Cloud Architectures
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : an instance has become exceedingly more time and resource consuming. To solve this issue, cloud computing is being used to train and serve the models. However, there’s a gap in research where these cloud computing platforms have been evaluated for these tasks. READ MORE
-
3. Comparative Analysis of Load Balancing in Cloud Platforms for an Online Bookstore Web Application using Apache Benchmark
University essay from Blekinge Tekniska Högskola/Institutionen för datavetenskapAbstract : Background :Cloud computing has transformed the landscape of application deploy-ment, offering on-demand access to compute resources, databases, and services viathe internet. This thesis explores the development of an innovative online book-storeweb application, harnessing the power of cloud infrastructure across AWS,Azure, andGCP. READ MORE
-
4. Knowledge-Based Engineering Application For Fuselage Integration And Cabin Design
University essay from Linköpings universitet/Fluida och mekatroniska systemAbstract : The pace of development in aviation technology is increasing, and there is a constantneed for new concepts to keep up. An innovative concept is desired to reach the netzero emission and sustainability target visualized in Flight path 2050. READ MORE
-
5. Comparison of Output Decoding Techniques for Spiking Neural Networks
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Spiking Neural Networks (SNNs) hold significant potential due to their high energy efficiency when implemented on specialized hardware. Central to SNNs is the translation of sequences of spike events to concrete outputs, like class predictions. READ MORE