Sökning: "Classification problem"

Visar resultat 16 - 20 av 849 uppsatser innehållade orden Classification problem.

1. 16. Evaluating the Viability of Synthetic Pre-training Data for Face Recognition Using a CNN-Based Multiclass Classifier

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

   Författare :Lars Bergström; Dag Hjelm; [2023]
   Nyckelord :;

   Sammanfattning : Today, face recognition is becoming increasingly accurate and faster with deep learning methods such as convolutional neural networks (CNNs), and is now widely used in areas such as security and entertainment. Typically, these CNNs are trained using real-face datasets like CASIA-WebFace, which was put together using web-crawling of IMDB. LÄS MER

3. 17. Exploration and Evaluation of RNN Models on Low-Resource Embedded Devices for Human Activity Recognition

   Master-uppsats, KTH/Mekatronik och inbyggda styrsystem

   Författare :Helgi Hrafn Björnsson; Jón Kaldal; [2023]
   Nyckelord :Recurrent Neural Networks; Long Short-Term Memory Networks; Embedded Systems; Human Activity Recognition; Edge AI; TensorFlow Lite Micro; Recurrent Neural Networks; Long Short-Term Memory Networks; Innbyggda systyem; Mänsklig aktivitetsigenkänning; Edge AI; TensorFlow Lite Micro;

   Sammanfattning : Human activity data is typically represented as time series data, and RNNs, often with LSTM cells, are commonly used for recognition in this field. However, RNNs and LSTM-RNNs are often too resource-intensive for real-time applications on resource constrained devices, making them unsuitable. LÄS MER

4. 18. 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

5. 19. Performance Benchmarking and Cost Analysis of Machine Learning Techniques : An Investigation into Traditional and State-Of-The-Art Models in Business Operations

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

   Författare :Jacob Lundgren; Sam Taheri; [2023]
   Nyckelord :Artificial Intelligence AI ; Machine Learning; Big Data; Natural Language Processing NLP ; Pre-Trained BERT; Fine-Tuned BERT; TF-IDF; Logistic Regression; Support Vector Machine SVM ; Cloud GPU; Operating Costs; Performance Efficiency; Business Intelligence;

   Sammanfattning : Eftersom samhället blir allt mer datadrivet revolutionerar användningen av AI och maskininlärning sättet företag fungerar och utvecklas på. Denna studie utforskar användningen av AI, Big Data och Natural Language Processing (NLP) för att förbättra affärsverksamhet och intelligens i företag. LÄS MER

7. 20. Machine Vision Based Quality Control and Fault Detection in a Textile Dyeing Machine

   Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Industriell elektroteknik och automation

   Författare :Evelina Morgan; Valter Möller; [2023]
   Nyckelord :Technology and Engineering;

   Sammanfattning : Fault detection systems come in a variety of formats and are used in many different types of machines and industries. They can be used to perform fast and accurate detection, classification and analysis. The need for user interaction can be decreased and by that the general level of automation can be increased. LÄS MER