Training algorithms for artificial neural networks depend on parameters called the hyperparameters. They can have a strong influence on the trained model but are often chosen manually with trial and error experiments. This thesis, conducted at Orange Labs Lannion, presents and evaluates three algorithms that aim at solving this task: a naive approach (random search), a Bayesian approach (Tree Parzen Estimator) and an evolutionary approach (Particle Swarm Optimization). A well-known dataset for handwritten digit recognition (MNIST) is used to compare these algorithms. These algorithms are also evaluated on audio classification, which is one of the main activities in the company team where the thesis was conducted. The evolutionary algorithm ...
This article describes an approach for solving the task of finding hyperparameters of an artificial ...
This project focuses on the concept of hyperparameters in a Machine Learning classifi- cation proble...
Radiotherapy of tumours depends on manually drawn maps of the tumours’ spread. A neural network for ...
Training algorithms for artificial neural networks depend on parameters called the hyperparameters. ...
This master thesis explores the feasibility of using genetic algorithms in order to automate the pro...
Artificial neural networks have been used to solve different problems, one being survival analysis o...
Abstract Hyperparameter tuning for Artificial Neural Network models is an important part in the proc...
Machine learning algorithms have many applications, both for academic and industrial purposes. Examp...
In order to create a machine learning model, one is often tasked with selecting certain hyperparamet...
Which numerical methods are ideal for training a neural network? In this report four different optim...
Machine learning and its wide range of applications is becoming increasingly prevalent in both acade...
Computer aided diagnostics (CAD) systems have been widely researched and used in the medical field s...
The analysis of vast amounts of data constitutes a major challenge in modern high energy physics exp...
Målene til denne masteroppgaven er: 1. Litteraturstudie på Gaussiske Prosesser (GP), Optimeringsteor...
Hyperparameter optimization in machine learning is a critical task that aims to find the hyper-param...
This article describes an approach for solving the task of finding hyperparameters of an artificial ...
This project focuses on the concept of hyperparameters in a Machine Learning classifi- cation proble...
Radiotherapy of tumours depends on manually drawn maps of the tumours’ spread. A neural network for ...
Training algorithms for artificial neural networks depend on parameters called the hyperparameters. ...
This master thesis explores the feasibility of using genetic algorithms in order to automate the pro...
Artificial neural networks have been used to solve different problems, one being survival analysis o...
Abstract Hyperparameter tuning for Artificial Neural Network models is an important part in the proc...
Machine learning algorithms have many applications, both for academic and industrial purposes. Examp...
In order to create a machine learning model, one is often tasked with selecting certain hyperparamet...
Which numerical methods are ideal for training a neural network? In this report four different optim...
Machine learning and its wide range of applications is becoming increasingly prevalent in both acade...
Computer aided diagnostics (CAD) systems have been widely researched and used in the medical field s...
The analysis of vast amounts of data constitutes a major challenge in modern high energy physics exp...
Målene til denne masteroppgaven er: 1. Litteraturstudie på Gaussiske Prosesser (GP), Optimeringsteor...
Hyperparameter optimization in machine learning is a critical task that aims to find the hyper-param...
This article describes an approach for solving the task of finding hyperparameters of an artificial ...
This project focuses on the concept of hyperparameters in a Machine Learning classifi- cation proble...
Radiotherapy of tumours depends on manually drawn maps of the tumours’ spread. A neural network for ...