Sökning: "training optimization"

Visar resultat 1 - 5 av 157 uppsatser innehållade orden training optimization.

1. 1. Evaluation of Deep Q-Learning Applied to City Environment Autonomous Driving

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Signaler och system

   Författare :Jonas Wedén; [2024]
   Nyckelord :Machine Learning; ML; Reinforcement Learning; RL; Neural Network; Deep Learning; Autonomous Vehicle; Vehicle; CARLA; Convolutional Neural Network; CNN; Precisit; Q-learning; Deep Q-learning; DQN;

   Sammanfattning : This project’s goal was to assess both the challenges of implementing the Deep Q-Learning algorithm to create an autonomous car in the CARLA simulator, and the driving performance of the resulting model. An agent was trained to follow waypoints based on two main approaches. LÄS MER

3. 2. Deep reinforcement learning for automated building climate control

   Master-uppsats, Linköpings universitet/Institutionen för datavetenskap

   Författare :Erik Snällfot; Martin Hörnberg; [2024]
   Nyckelord :Machine Learning; Reinforcement Learning; Deep Learning; Deep Reinforcement Learning; Building Control; Control System;

   Sammanfattning : The building sector is the single largest contributor to greenhouse gas emissions, making it a natural focal point for reducing energy consumption. More efficient use of energy is also becoming increasingly important for property managers as global energy prices are skyrocketing. LÄS MER

4. 3. Optimising Machine Learning Models for Imbalanced Swedish Text Financial Datasets: A Study on Receipt Classification : Exploring Balancing Methods, Naive Bayes Algorithms, and Performance Tradeoffs

   Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

   Författare :Li Ang Hu; Long Ma; [2023]
   Nyckelord :Imbalanced datasets; Swedish text financial datasets; Accuracy; Matthews correlation coefficient; Recall; Multinomial Naive Bayes; SMOTE; TomekLinks; Performance optimization;

   Sammanfattning : This thesis investigates imbalanced Swedish text financial datasets, specifically receipt classification using machine learning models. The study explores the effectiveness of under-sampling and over-sampling methods for Naive Bayes algorithms, collaborating with Fortnox for a controlled experiment. LÄS MER

5. 4. EMONAS : Evolutionary Multi-objective Neuron Architecture Search of Deep Neural Network

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

   Författare :Jiayi Feng; [2023]
   Nyckelord :DNN Deep Neural Network ; NAS Neural Architecture Search ; EA Evolutionary Algorithm ; Multi-Objective Optimization; Binary One Optimization; Embedded Systems; DNN Deep Neural Network ; NAS Neural Architecture Search ; EA Evolutionary Algorithm ; Multi-Objective Optimization; Binary One Optimization; Inbyggda system;

   Sammanfattning : Customized Deep Neural Network (DNN) accelerators have been increasingly popular in various applications, from autonomous driving and natural language processing to healthcare and finance, etc. However, deploying them directly on embedded system peripherals within real-time operating systems (RTOS) is not easy due to the paradox of the complexity of DNNs and the simplicity of embedded system devices. LÄS MER

7. 5. 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