dependent output variables and structured output spaces. We propose to generalize multiclass Support Vector Machine learning in a formulation that involves features extracted jointly from inputs and outputs. The resulting optimization problem is solved efficiently by a cutting plane algorithm that exploits

Learning general functional dependencies between arbitrary input and output spaces is one of the key challenges in computational intelligence. While recent progress in machine learning has mainly focused on designing flexible and powerful input representations, this paper addresses

suffer when mining databases of large graphs. Another motivation is to obtain a succinct output set that is informative and useful. In the same spirit, researchers also proposed sampling based algorithms that sample the output space of the frequent patterns to obtain representative subgraphs

We investigate multi-task learning from an output space regularization perspective. Most multi-task approaches tie together related tasks by constraining them to share input spaces and function classes. In contrast to this, we propose a multi-task paradigm which we call output space regularization

A general framework is proposed for gradient boosting in supervised learning problems where the loss function is defined using a kernel over the output space. It extends boosting in a principled way to complex output spaces (images, text, graphs etc.) and can be applied to a general class of base

Abstract We consider a framework for structured prediction based on search in the space of complete structured outputs. Given a structured input, an output is produced by running a time-bounded search procedure guided by a learned cost function, and then returning the least cost output uncovered

HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Abstract Multi-label classification is a generalization of binary classification where the task consists in predicting sets of labels. With the availability of ever larger datasets, the multi-label setting has become a natural one in many applications, and the interest in solving multi-label problems has grown significantly. As expected, deep learning approaches are now yielding state-of-the-art performance for this class of problems. Unfortunately, they usually do not take into account the often unknown but nevertheless rich relationships between labels. In this paper, we propose to make use of this underlying structure by learning to partition the labels into a Markov Blanket Chain and then applying a novel deep architecture that exploits the partition. Experiments on several popular and large multi-label datasets demonstrate that our approach not only yields significant improvements, but also helps to overcome trade-offs specific to the multi-label classification setting.

motion mechanisms in which the first stage consists of linear filters that are oriented in space-time and tuned in spatial frequency. The outputs of quadrature pairs of such filters are squared and summed to give a measure of motion energy. These responses are then fed into an opponent stage. Energy

Neural maps project data given in a (possibly high-dimensional) input space onto a neuron position in a (usually low-dimensional) output space grid. An important property of this projection is the preservation of neighborhoods; neighboring neurons in output space respond to neighboring data points