Sökning: "Saliency Maps"
Visar resultat 1 - 5 av 9 uppsatser innehållade orden Saliency Maps.
1. PVCFA: Principal Variation Context Feature Attribution : Distributed Chess for Perturbation-based Saliency Maps
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The research and development field of computer chess improved more in the last 5 years than in the whole history of computers. Unfortunately these unprecedented results comes with techniques that don’t leave much space to intuition and comprehensibility for humans. LÄS MER
2. Saliency driven lossy image compression using machine learning
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Since the introduction of digital media for consumers in the 1990s, the amount of images used in everyday life has grown exponentially. All these images need to be stored and broadcasted from some storage device, which has been made possible with the use of image compression algorithms such as JPG. LÄS MER
3. Tailored Deep Degression for use on MRI-Scan Analysis
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för visuell information och interaktionSammanfattning : UK Biobank is a British clinical study containing over 40 000 Magnetic Resonance Images (MRI) with 100 000 MRI planned of participants aged 44-82 as well as a large amount of related medical data. Analyzing these images with a neural network to find relations between the information in an MRI image and various medical data could lead to interesting medical revelations. LÄS MER
4. Comparing Human Reasoning and Explainable AI
Kandidat-uppsats, Malmö universitet/Institutionen för datavetenskap och medieteknik (DVMT)Sammanfattning : Explainable AI (XAI) is a research field dedicated to formulating avenues of breaching the black box nature of many of today’s machine learning models. As society finds new ways of applying these models in everyday life, certain risk thresholds are crossed when society replaces human decision making with autonomous systems. LÄS MER
5. Zero/Few-Shot Text Classification : A Study of Practical Aspects and Applications
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : SOTA language models have demonstrated remarkable capabilities in tackling NLP tasks they have not been explicitly trained on – given a few demonstrations of the task (few-shot learning), or even none at all (zero-shot learning). The purpose of this Master’s thesis has been to investigate practical aspects and potential applications of zero/few-shot learning in the context of text classification. LÄS MER