Sökning: "backpropagation algorithms"

Visar resultat 1 - 5 av 20 uppsatser innehållade orden backpropagation algorithms.

1. 1. Estimation of dissolved organic carbon from inland waters using remote sensing data and machine learning

   Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskap

   Författare :Lasse Harkort; [2022]
   Nyckelord :dissolved organic carbon; machine learning; remote sensing; inland waters; water quality; open source data; Earth and Environmental Sciences;

   Sammanfattning : This thesis presents the first attempt to estimate Dissolved Organic Carbon (DOC) in inland waters over a large-scale area using satellite data and machine learning (ML) methods. Four ML approaches, namely Random Forest Regression (RFR), Support Vector Regression (SVR), Gaussian Process Regression (GPR), and a Multilayer Backpropagation Neural Network (MBPNN) were tested to retrieve DOC using a filtered version of the recently published open source AquaSat dataset with more than 16 thousand samples across the continental US matched with satellite data from Landsat 5, 7 and 8 missions. LÄS MER

3. 2. Building and Training a Fully Connected Deep Neural Network From Scratch

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

   Författare :Axel Berglund; [2022]
   Nyckelord :Deep Neural Network; Machine Learning; Gradient Decent; MNIST.;

   Sammanfattning : Artificial Neural Networks make up the core of mostMachine Learning algorithms. In the past decade Machine learninghave successfully taken on fields such as image recognition,Data analytics and medical technologies. LÄS MER

4. 3. Spiking Reinforcement Learning for Robust Robot Control Under Varying Operating Conditions

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

   Författare :Philipp Mondorf; [2022]
   Nyckelord :;

   Sammanfattning : Over the last few years, deep reinforcement learning (RL) has gained increasing popularity for its successful application to a variety of complex control and decision-making tasks. As the demand for deep RL algorithms deployed in challenging real-world environments grows, their robustness towards uncertainty, disturbances and perturbations of the environment becomes more and more important. LÄS MER

5. 4. The derivation of first- and second-order backpropagation methods for fully-connected and convolutional neural networks

   Master-uppsats, Lunds universitet/Matematik LTH; Lunds universitet/Matematikcentrum

   Författare :Simon Sjögren; [2021]
   Nyckelord :Mathematics and Statistics;

   Sammanfattning : We introduce rigorous theory for deriving first and second order backpropagation methods for Deep Neural Networks (DNN) whilst satisfying existing theory in DNN optimization. We begin by formally defining a neural network with its respective components and state the first and second order chain rule with respect to its partial derivatives. LÄS MER

7. 5. Neurala nätverk försjälvkörande fordon : Utforskande av olika tillvägagångssätt

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

   Författare :Simon Hellner; Henrik Syvertsson; [2021]
   Nyckelord :artificial neural networks; gradient descent; genetic algorithm; backpropagation; unity; self driving; autonomous vehicles; line detection; neural network; neural net; artificiella neurala nätverk; neurala nätverk; självkörande bilar; självkörande fordon; unity; bakåtpropagering; linjedetektering; gradient descent; genetisk algoritm; neurala nät;

   Sammanfattning : Artificiella neurala nätverk (ANN) har ett brett tillämpningsområde och blir allt relevantare på flera håll, inte minst för självkörande fordon. För att träna nätverken användsmeta-algoritmer. Nätverken kan styra fordonen med hjälp av olika typer av indata. LÄS MER