Sökning: "AI models"

Visar resultat 1 - 5 av 415 uppsatser innehållade orden AI models.

  1. 1. Feature Selection for Microarray Data via Stochastic Approximation

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Erik Rosvall; [2024-03-18]
    Nyckelord :feature selection; feature ranking; microarray data; stochastic approximation; Barzilai and Borwein method; Machine Learning; AI;

    Sammanfattning : This thesis explores the challenge of feature selection (FS) in machine learning, which involves reducing the dimensionality of data. The selection of a relevant subset of features from a larger pool has demonstrated its effectiveness in enhancing the performance of various machine learning algorithms. LÄS MER

  3. 2. BILDEN AV AI- FRÅN MYT TILL VERKLIGHET. En kvantitativ innehållsanalys av svenska nyhetsmediers gestaltning av artificiell intelligens

    Kandidat-uppsats, Göteborgs universitet/Institutionen för journalistik, medier och kommunikation

    Författare :Johann Rothoff; Ina Wikström Hellberg; [2024-03-04]
    Nyckelord :Artificiell intelligens AI ; gestaltningsteorin; emerging technologies; nyhetsmedia; aktörer; OpenAI;

    Sammanfattning : Executive summary The purpose of this study was to explore how artificial intelligence (AI) has been framed in the Swedish news media through the course of time. Although the first definition dates back to the 1950’s, AI can still be considered a rather early concept when seen as an emerging technology. LÄS MER

  4. 3. Optical Communication using Nanowires and Molecular Memory Systems

    Master-uppsats, Lunds universitet/Fysiska institutionen; Lunds universitet/Synkrotronljusfysik

    Författare :Thomas Kjellberg Jensen; [2024]
    Nyckelord :neuromorphic computing; nanowire; molecular dye; DASA photoswitch; OBIC; Physics and Astronomy;

    Sammanfattning : Neuromorphic computational networks, inspired by biological neural networks, provide a possible way of lowering computational energy cost, while at the same time allowing for much more sophisticated devices capable of real-time inferences and learning. Since simulating artificial neural networks on conventional computers is particularly inefficient, the development of neuromorphic devices is strongly motivated as the reliance on AI-models increases. LÄS MER

  5. 4. Automating the identification of components in 3D models

    Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Författare :Oliver Olofsson; [2024]
    Nyckelord :Part segmentation; Blender; 3D mesh; MeshCNN; PointNet ; DGCNN;

    Sammanfattning : Online house building tools are robust instruments that have transformed the approach to home planning and design. The significance of 3D models on online house building and design platforms lies in their ability to elevate the user experience, enhance design precision, and foster collaboration. LÄS MER

  7. 5. ML implementation for analyzing and estimating product prices

    Kandidat-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

    Författare :Abel Getachew Kenea; Gabriel Fagerslett; [2024]
    Nyckelord :Machine Learning; ML; Regression; Deep Learning; Artificial Neural Network; ANN; TensorFlow; ScikitLearn; CUDA; cuDNN; Estimation; Prediction; AI; Artificial Intelligence; Price Tracking; Price Logging; Price Estimation; Supervised Learning; Random Forest; Decision Trees; Batch Learning; Hyperparameter Tuning; Linear Regression; Multiple Linear Regression; Maskininlärning; Djup lärning; Artificiellt Neuralt Nätverk; Regression; TensorFlow; SciktLearn; ML; ANN; Estimation; Uppskattning; CUDA; cuDNN; AI; Artificiell Intelligens; pris loggning; pris estimation; prisspårning; Batchinlärning; Hyperparameterjustering; Linjär Regression; Multipel Linjär Regression; Supervised Learning; Random Forest; Decision Trees;

    Sammanfattning : Efficient price management is crucial for companies with many different products to keep track of, leading to the common practice of price logging. Today, these prices are often adjusted manually, but setting prices manually can be labor-intensive and prone to human error. LÄS MER