Search results for "supervised learning"
showing 10 items of 87 documents
Semi-Supervised Classification Method for Hyperspectral Remote Sensing Images
2004
A new approach to the classification of hyperspectral images is proposed. The main problem with supervised methods is that the learning process heavily depends on the quality of the training data set. In remote sensing, the training set is useful only for simultaneous images or for images with the same classes taken under the same conditions; and, even worse, the training set is frequently not available. On the other hand, unsupervised methods are not sensitive to the number of labelled samples since they work on the whole image. Nevertheless, relationship between clusters and classes is not ensured. In this context, we propose a combined strategy of supervised and unsupervised learning met…
Review on Machine Learning Based Lesion Segmentation Methods from Brain MR Images
2016
Brain lesions are life threatening diseases. Traditional diagnosis of brain lesions is performed visually by neuro-radiologists. Nowadays, advanced technologies and the progress in magnetic resonance imaging provide computer aided diagnosis using automated methods that can detect and segment abnormal regions from different medical images. Among several techniques, machine learning based methods are flexible and efficient. Therefore, in this paper, we present a review on techniques applied for detection and segmentation of brain lesions from magnetic resonance images with supervised and unsupervised machine learning techniques.
The Engineering of a Compression Boosting Library: Theory vs Practice in BWT Compression
2006
Data Compression is one of the most challenging arenas both for algorithm design and engineering. This is particularly true for Burrows and Wheeler Compression a technique that is important in itself and for the design of compressed indexes. There has been considerable debate on how to design and engineer compression algorithms based on the BWT paradigm. In particular, Move-to-Front Encoding is generally believed to be an "inefficient " part of the Burrows-Wheeler compression process. However, only recently two theoretically superior alternatives to Move-to-Front have been proposed, namely Compression Boosting and Wavelet Trees. The main contribution of this paper is to provide the first ex…
Contrastive Learning with Continuous Proxy Meta-data for 3D MRI Classification
2021
Traditional supervised learning with deep neural networks requires a tremendous amount of labelled data to converge to a good solution. For 3D medical images, it is often impractical to build a large homogeneous annotated dataset for a specific pathology. Self-supervised methods offer a new way to learn a representation of the images in an unsupervised manner with a neural network. In particular, contrastive learning has shown great promises by (almost) matching the performance of fully-supervised CNN on vision tasks. Nonetheless, this method does not take advantage of available meta-data, such as participant’s age, viewed as prior knowledge. Here, we propose to leverage continuous proxy me…
Modeling the Target-Note Technique of Bebop-Style Jazz Improvisation: An Artificial Neural Network Approach
1995
In cognitive science and research on artificial intelligence, there are two central paradigms: symbolic and analogical. Within the analogical paradigm, artificial neural networks (ANNs) have recently been successfully used to model and simulate cognitive phenomena. One of the most prominent features of ANNs is their ability to learn by example and, to a certain extent, generalize what they have learned. Improvisation, the art of spontaneously creating music while playing or singing, fundamentally has an imitative nature. Regardless of how much one studies and analyzes, the art of improvisation is learned mostly by example. Instead of memorizing explicit rules, the student mimics the playing…
Using deep neural networks for kinematic analysis: Challenges and opportunities
2020
Kinematic analysis is often performed in a lab using optical cameras combined with reflective markers.\ud With the advent of artificial intelligence techniques such as deep neural networks, it is now possible\ud to perform such analyses without markers, making outdoor applications feasible. In this paper I summarise\ud 2D markerless approaches for estimating joint angles, highlighting their strengths and limitations.\ud In computer science, so-called ‘‘pose estimation” algorithms have existed for many years. These methods\ud involve training a neural network to detect features (e.g. anatomical landmarks) using a process called\ud supervised learning, which requires ‘‘training” images to be …
Visual aftereffects and sensory nonlinearities from a single statistical framework
2015
When adapted to a particular scenery our senses may fool us: colors are misinterpreted, certain spatial patterns seem to fade out, and static objects appear to move in reverse. A mere empirical description of the mechanisms tuned to color, texture, and motion may tell us where these visual illusions come from. However, such empirical models of gain control do not explain why these mechanisms work in this apparently dysfunctional manner. Current normative explanations of aftereffects based on scene statistics derive gain changes by (1) invoking decorrelation and linear manifold matching/equalization, or (2) using nonlinear divisive normalization obtained from parametric scene models. These p…
Retrieving Quantum Information with Active Learning
2019
Active learning is a machine learning method aiming at optimal design for model training. At variance with supervised learning, which labels all samples, active learning provides an improved model by labeling samples with maximal uncertainty according to the estimation model. Here, we propose the use of active learning for efficient quantum information retrieval, which is a crucial task in the design of quantum experiments. Meanwhile, when dealing with large data output, we employ active learning for the sake of classification with minimal cost in fidelity loss. Indeed, labeling only 5% samples, we achieve almost 90% rate estimation. The introduction of active learning methods in the data a…
Contribution à l’apprentissage de représentation de données à base de graphes avec application à la catégorisation d’images
2020
Graph-based Manifold Learning algorithms are regarded as a powerful technique for feature extraction and dimensionality reduction in Pattern Recogniton, Computer Vision and Machine Learning fields. These algorithms utilize sample information contained in the item-item similarity and weighted matrix to reveal the intrinstic geometric structure of manifold. It exhibits the low dimensional structure in the high dimensional data. This motivates me to develop Graph-based Manifold Learning techniques on Pattern Recognition, specially, application to image categorization. The experimental datasets of thesis correspond to several categories of public image datasets such as face datasets, indoor and…
A Pseudo-Supervised Approach to Improve a Recommender Based on Collaborative Filtering
2003
This PhD Thesis develops an optimal recommender. First of all, users accessing to a Web site are clustered. If a user belongs to a cluster, the system offers services which are usually accessed by users from the same cluster in a collaborative filtering scheme. A novel approach based on a users simulator and a dynamic recommendation system is proposed. The simulator is used to create the situations that one can find in a Web site. Introduction of dynamics in the recommender allows to change the clusters and in turn, the decisions which are taken. Since the system is based both on supervised and unsupervised learning whose borders are not too clear in our approach, we talk about a pseudo-sup…