Efficient Sparse Subspace Clustering via Matrix Completion – While Convolutional neural networks (CNNs) have become the most explored and powerful tool for supervised learning on image data, little attention has been focused on the learning of sparse representations. In this paper, we investigate sparse representation learning and learn sparse representations from high-dimensional data, using the deep CNN family. We exploit the fact that the embedding space of a CNN representation can only contain sparse information, and not the underlying image representation. We propose an efficient method to learn sparse representations in CNNs using a deep CNN architecture. We study the nonlinearity of the embedding space and the problem of learning sparse representations in CNNs. We derive a novel deep learning method that significantly improves the performance when compared to conventional CNN-based approaches.

Probabilistic modeling and inference techniques in general are well-suited to infer, understand and reason from complex data. Here, we propose the use of Bayesian inference to model data and provide tools for inferring and reasoning from complex data sets. This paper also presents a new system for probabilistic inference where data is represented as a continuous vector space and inference is carried out from a high-dimensional feature space. The main contributions of this paper are: (1) The Bayesian inference process is based on a nonparametric structure, a generalization of Markovian logic semantics and the conditional probability measure is derived, which provides a framework for Bayesian inference which allows to model complex data. (2) Further, the use of the conditional probability measure and conditional conditional inference are both derived using the nonparametric structure underlying Bayesian inference algorithms. (3) We provide an implementation of the probabilistic inference system by integrating the Bayesian inference inference algorithm into a machine learning platform for Bayesian learning experiments based on neural networks and machine learning algorithms.

Spatially Aware Convolutional Neural Networks for Person Re-Identification

Predicting the outcome of long distance triathlons by augmentative learning

# Efficient Sparse Subspace Clustering via Matrix Completion

LSTM Convolutional Neural Networks

Efficient Online Sufficient Statistics for Transfer in Machine Learning with Deep LearningProbabilistic modeling and inference techniques in general are well-suited to infer, understand and reason from complex data. Here, we propose the use of Bayesian inference to model data and provide tools for inferring and reasoning from complex data sets. This paper also presents a new system for probabilistic inference where data is represented as a continuous vector space and inference is carried out from a high-dimensional feature space. The main contributions of this paper are: (1) The Bayesian inference process is based on a nonparametric structure, a generalization of Markovian logic semantics and the conditional probability measure is derived, which provides a framework for Bayesian inference which allows to model complex data. (2) Further, the use of the conditional probability measure and conditional conditional inference are both derived using the nonparametric structure underlying Bayesian inference algorithms. (3) We provide an implementation of the probabilistic inference system by integrating the Bayesian inference inference algorithm into a machine learning platform for Bayesian learning experiments based on neural networks and machine learning algorithms.

## Leave a Reply