Sökning: "Distributional Learning"
Visar resultat 1 - 5 av 14 uppsatser innehållade orden Distributional Learning.
1. Restaurant Daily Revenue Prediction : Utilizing Synthetic Time Series Data for Improved Model Performance
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för beräkningsvetenskapSammanfattning : This study aims to enhance the accuracy of a demand forecasting model, XGBoost, by incorporating synthetic multivariate restaurant time series data during the training process. The research addresses the limited availability of training data by generating synthetic data using TimeGAN, a generative adversarial deep neural network tailored for time series data. LÄS MER
2. ElektroCHAT: A Knowledge Base-Driven Dialogue System for Electrical Engineering Students : A Proposal for Interactive Tutoring
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Universities worldwide face challenges both with students dropping out of educational programmes and repetitive questions directed toward teaching staff which both consume resources and result in delays. Recent progress in natural language processing (NLP) introduces the possibility of more sophisticated dialogue systems that could help alleviate the situation. LÄS MER
3. Risk-Sensitive Decision-Making for Autonomous-Driving
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : A natural aspect of the real world is that one can face uncertain situations on a daily basis. Depending on one's experience, we humans behave and respond differently to uncertainty. However, when designing intelligent agents, one needs to pay attention to the uncertainty inlearning tasks to design risk-sensitive algorithms. LÄS MER
4. Learning from Synthetic Data : Towards Effective Domain Adaptation Techniques for Semantic Segmentation of Urban Scenes
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Semantic segmentation is the task of predicting predefined class labels for each pixel in a given image. It is essential in autonomous driving, but also challenging because training accurate models requires large and diverse datasets, which are difficult to collect due to the high cost of annotating images at pixel-level. LÄS MER
5. Interactionwise Semantic Awareness in Visual Relationship Detection
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Visual Relationship Detection (VRD) is a relatively young research area, where the goal is to develop prediction models for detecting the relationships between objects depicted in an image. A relationship is modeled as a subject-predicate-object triplet, where the predicate (e.g an action, a spatial relation, etc. LÄS MER