Add to ORKGKnowing how to exploit unlabeled data is a fundamental problem in machine learning. This dissertation provides contributions in different contexts, including semi-supervised learning, positive unlabeled learning and representation learning. In particular, we ask (i) whether is possible to learn a classifier in the context of limited data, (ii) whether is possible to scale existing models for positive unlabeled learning, and (iii) whether is possible to train a deep generative model with a single minimization problem
International audienceThis paper investigates a new approach for training discriminant classifiers w...
We consider the semi-supervised learning problem, where a decision rule is to be learned from labele...
Semi-supervised learning can be applied to datasets that contain both labeled and unlabeled instance...
This thesis focuses on how unlabeled data can improve supervised learning classi-fiers in all contex...
In the general framework of semi-supervised learning from labeled and unlabeled data, we consider ...
The Problem: Learning from data with both labeled training points (x,y pairs) and unlabeled training...
We consider the general problem of learning from labeled and unlabeled data, which is often called s...
Semi-supervised learning is the learning setting in which we have both labeled and unlabeled data at...
We present a new machine learning framework called “self-taught learning ” for using unlabeled data ...
We present a new machine learning framework called “self-taught learning ” for using unlabeled data ...
We consider the semi-supervised learning problem, where a decision rule is to be learned from labele...
Developing partially supervised models is becoming increasingly relevant in the context of modern ma...
Göpfert C, Ben-David S, Bousquet O, Gelly S, Tolstikhin I, Urner R. When can unlabeled data improve ...
Developing partially supervised models is becoming increasingly relevant in the context of modern ma...
In semi-supervised learning (SSL), a common practice is to learn consistent information from unlabel...
International audienceThis paper investigates a new approach for training discriminant classifiers w...
We consider the semi-supervised learning problem, where a decision rule is to be learned from labele...
Semi-supervised learning can be applied to datasets that contain both labeled and unlabeled instance...
This thesis focuses on how unlabeled data can improve supervised learning classi-fiers in all contex...
In the general framework of semi-supervised learning from labeled and unlabeled data, we consider ...
The Problem: Learning from data with both labeled training points (x,y pairs) and unlabeled training...
We consider the general problem of learning from labeled and unlabeled data, which is often called s...
Semi-supervised learning is the learning setting in which we have both labeled and unlabeled data at...
We present a new machine learning framework called “self-taught learning ” for using unlabeled data ...
We present a new machine learning framework called “self-taught learning ” for using unlabeled data ...
We consider the semi-supervised learning problem, where a decision rule is to be learned from labele...
Developing partially supervised models is becoming increasingly relevant in the context of modern ma...
Göpfert C, Ben-David S, Bousquet O, Gelly S, Tolstikhin I, Urner R. When can unlabeled data improve ...
Developing partially supervised models is becoming increasingly relevant in the context of modern ma...
In semi-supervised learning (SSL), a common practice is to learn consistent information from unlabel...
International audienceThis paper investigates a new approach for training discriminant classifiers w...
We consider the semi-supervised learning problem, where a decision rule is to be learned from labele...
Semi-supervised learning can be applied to datasets that contain both labeled and unlabeled instance...