Sökning: "learning toy"

Visar resultat 1 - 5 av 28 uppsatser innehållade orden learning toy.

1. 1. On Linear Mode Connectivity up to Permutation of Hidden Neurons in Neural Network : When does Weight Averaging work?

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Adhithyan Kalaivanan; [2023]
   Nyckelord :Mode Connectivity; Representation Learning; Loss Landscape; Network Symmetry; Lägesanslutning; representationsinlärning; förlustlandskap; nätverkssymmetri;

   Sammanfattning : Neural networks trained using gradient-based optimization methods exhibit a surprising phenomenon known as mode connectivity, where two independently trained network weights are not isolated low loss minima in the parameter space. Instead, they can be connected by simple curves along which the loss remains low. LÄS MER

3. 2. An Open-Source Autoencoder Compression Tool for High Energy Physics

   Magister-uppsats, Lunds universitet/Partikel- och kärnfysik; Lunds universitet/Fysiska institutionen

   Författare :Axel Gallén; [2023]
   Nyckelord :Physics; Particle Physics; Analysis; Machine Learning; Neural Networks; Autoencoders; Data Compression; Lossy Compression; Baler; Physics and Astronomy;

   Sammanfattning : A common problem across scientific fields and industries is data storage. This thesis presents an open-source lossy data compression tool with its foundation in Machine Learning - Baler. Baler has been used to compress High Energy Physics (HEP) data, and initial compression tests on Computational Fluid Dynamics (CFD) toy data have been performed. LÄS MER

4. 3. Messing With The Gap: On The Modality Gap Phenomenon In Multimodal Contrastive Representation Learning

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Industriell teknik

   Författare :Mohammad Al-Jaff; [2023]
   Nyckelord :Multimodal machine learning; Representation learning; Self-supervised learning; contrastive learning; computer vision; computational biology; bioinformatics;

   Sammanfattning : In machine learning, a sub-field of computer science, a two-tower architecture model is a specialised type of neural network model that encodes paired data from different modalities (like text and images, sound and video, or proteomics and gene expression profiles) into a shared latent representation space. However, when training these models using a specific contrastive loss function, known as the multimodalinfoNCE loss, seems to often lead to a unique geometric phenomenon known as the modality gap. LÄS MER

5. 4. Levande djur i förskolan : En kvalitativ studie om hur en afrikansk jättelandsnäcka bidrar till undervisningen i förskolan

   Uppsats för yrkesexamina på grundnivå, Karlstads universitet/Institutionen för pedagogiska studier (from 2013)

   Författare :Helene Pollmeier; Emmy Zetterberg; [2022]
   Nyckelord :biology; education; living animals; posthumanism; preschool; biologi; förskola; levande djur; posthumanism; undervisning;

   Sammanfattning : Studien har fokus på barns perspektiv och syftet med studien är att undersöka vad ett levande djur bidrar med i en undervisningssituation för äldre förskolebarn. Metoden som används i studien är observation av en undervisningsaktivitet med en efterföljande semistrukturerad gruppintervju. LÄS MER

7. 5. Analyzing the Negative Log-Likelihood Loss in Generative Modeling

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Aleix Espuña I Fontcuberta; [2022]
   Nyckelord :Generative modeling; Normalizing flows; Generative Adversarial Networks; MaximumLikelihood Estimation; Real Non-Volume Preserving flow; Fréchet Inception Distance; Misspecification; Generativa metoder; Normalizing flows; Generative adversarial networks; Maximum likelihood-metoden; Real non-volume preserving flow; Fréchet inception distance; felspecificerade modeller;

   Sammanfattning : Maximum-Likelihood Estimation (MLE) is a classic model-fitting method from probability theory. However, it has been argued repeatedly that MLE is inappropriate for synthesis applications, since its priorities are at odds with important principles of human perception, and that, e.g. LÄS MER