Sökning: "super size"
Visar resultat 1 - 5 av 50 uppsatser innehållade orden super size.
1. Trainable Region of Interest Prediction: Hard Attention Framework for Hardware-Efficient Event-Based Computer Vision Neural Networks on Neuromorphic Processors
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : Neuromorphic processors are a promising new type of hardware for optimizing neural network computation using biologically-inspired principles. They can effectively leverage information sparsity such as in images from event-based cameras, and are well-adapted to processing event-based data in an energy-efficient fashion. LÄS MER
2. Stabilizing Side Effects of Experience Replay With Different Network Sizes for Deep Q-Network
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This report investigates the effects of two different types of batch selection used for traininga Deep Reinforcement Learning agent in games. More specifically, the impact of thedifferent methods were tested for different sizes of Deep Neural Networks while using theDeep Q-Network (DQN) algorithm. LÄS MER
3. Simulations of the Tenuous Upper Atmospheres of Exoplanets
Master-uppsats, Lunds universitet/Astrofysik; Lunds universitet/Fysiska institutionenSammanfattning : Over the last decade, the interest in research on extraterrestrial planets has expanded dramatically. With the number of confirmed exoplanets having increased tenfold over the last ten years, we now know that many different types of exoplanets exist. LÄS MER
4. Techno-economic fesibility of a hybrid CSP (sCO2) - PV plant for hydrogen production
Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)Sammanfattning : The global need to eliminate CO2 emissions and its consequent reduction in the use of fossil fuels drives the ongoing energy transition that highly involves the research achievements of the scientific community to reach the goals of this purpose. Renewable sources like photovoltaic and wind energy, are central to this endeavor, however, the intermittency of natural resources makes it non-dispatchable and energy storage is fundamental. LÄS MER
5. Using Quantization and Serialization to Improve AI Super-Resolution Inference Time on Cloud Platform
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : AI Super-Resolution is a branch of Artificial Intelligence where the goal is to take a low-resolution image and upscale it into a high-resolution image. These models are usually deep learning models based on Convolutional Neural Networks (CNN) and/or transformers. LÄS MER