Advanced search
Showing result 1 - 5 of 10 essays matching the above criteria.
-
1. Scene Reconstruction From 4D Radar Data with GAN and Diffusion : A Hybrid Method Combining GAN and Diffusion for Generating Video Frames from 4D Radar Data
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 4D Imaging Radar is increasingly becoming a critical component in various industries due to beamforming technology and hardware advancements. However, it does not replace visual data in the form of 2D images captured by an RGB camera. READ MORE
-
2. EVALUATING PERFORMANCE OF GENERATIVE MODELS FOR TIME SERIES SYNTHESIS
University essay from Mälardalens universitet/Akademin för innovation, design och teknikAbstract : Motivated by successes in the image generation domain, this thesis presents a novel Hybrid VQ-VAE (H-VQ-VAE) approach for generating realistic synthetic time series data with categorical features. The primary motivation behind this work is to address the limitations of existing generative models in accurately capturing the underlying structure and patterns of time series data, especially when dealing with categorical features. READ MORE
-
3. Utilizing GPT for Interactive Dialogue-based Learning Scenarios : A Comparative Analysis with Rasa
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This thesis explores the use of advanced language models, specifically OpenAI’s Generative Pretrained Transformer (GPT), in the context of interactive tutoring systems built within a Unity-based game environment. The central problem addressed is whether the recent advancements in large language models make them feasible and useful to function as tutors specifically in providing meaningful, engaging, and educationally rich user interactions on a dialogue based learning platform developed by Fictive Reality. READ MORE
-
4. Towards Deep Learning Accelerated Sparse Bayesian Frequency Estimation
University essay from Lunds universitet/Matematisk statistikAbstract : The Discrete Fourier Transform is the simplest way to obtain the spectrum of a discrete complex signal. This thesis concerns the case when the signal is known to contain a small (unknown) number of frequencies, not limited to the discrete Fourier frequencies, embedded in complex Gaussian noise. READ MORE
-
5. Unsupervised 3D Human Pose Estimation
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : The thesis proposes an unsupervised representation learning method to predict 3D human pose from a 2D skeleton via a VAEGAN (Variational Autoencoder Generative Adversarial Network) hybrid network. The method learns to lift poses from 2D to 3D using selfsupervision and adversarial learning techniques. READ MORE
