Sökning: "Decoder"
Visar resultat 1 - 5 av 162 uppsatser innehållade ordet Decoder.
1. Gendered Language in English Job Advertisements and the Perception of Potential Applicants within Electrical and Electronic Engineering in Sweden
Kandidat-uppsats, Mälardalens universitet/Akademin för utbildning, kultur och kommunikationSammanfattning : This mixed-method study investigates the use of masculine and feminine-coded words (i.e., words associated with gender stereotypes) in English job advertisements in Sweden, focusing on the male-dominated Electronic and Electric engineering field in Sweden (SCB, 2022). LÄS MER
2. Where to Fuse
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : This thesis investigates fusion techniques in multimodal transformer models, focusing on enhancing the capabilities of large language models in understanding not just text, but also other modalities like images, audio, and sensor data. The study compares late fusion (concatenating modality tokens after separate encoding) and early fusion (concatenating before encoding) techniques, examining their respective advantages and disadvantages. LÄS MER
3. Transforming Chess: Investigating Decoder-Only Architecture for Generating Realistic Game-Like Positions
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : Chess is a deep and intricate game, the master of which depends on learning tens of thousands of the patterns that may occur on the board. At Noctie, their mission is to aid this learning process through humanlike chess AI. A prominent challenge lies in curating instructive chess positions for students. LÄS MER
4. Evaluating and optimizing Transformer models for predicting chemical reactions
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : In this thesis, we assess the effectiveness of a transformer model specifically trained to predict chemical reactions. The model, named Chemformer, is a sequence-tosequence model that uses the transformer’s encoder and decoder stacks. LÄS MER
5. Decoding the surface code using graph neural networks
Master-uppsats, Göteborgs universitet / Institutionen för fysikSammanfattning : Quantum error correction is essential to achieve fault-tolerant quantum computation in the presence of noisy qubits. Among the most promising approaches to quantum error correction is the surface code, thanks to a scalable two-dimensional architecture, only nearest-neighbor interactions, and a high error threshold. Decoding the surface code, i.e. LÄS MER