A major issue in statistical machine learning is the design of a representation, or feature space, facilitating the resolution of the learning task at hand. Sparse representations in particular facilitate discriminant learning: On the one hand, they are robust to noise. On the other hand, they disentangle the factors of variation mixed up in dense representations, favoring the separability and ...

Everyday, millions of short-texts are generated for which effective tools for organization and retrieval are required. Because of the tiny length of these documents and of their extremely sparse representations, the direct application of standard text categorization methods is not effective. In this work we propose using distributional term representations (DTRs) for short-text categorization. ...

During the last decade, sparse representations have been successfully applied to design highperforming classification algorithms such as the classical sparse representation based classification (SRC) algorithm. More recently, collaborative representation based classification (CRC) has emerged as a very powerful approach, especially for face recognition. CRC takes advantage of sparse representat...

Deep learning is regarded by some as one of the most important technological breakthroughs of this decade. In recent years it has been shown that using rectified neurons, one can match or surpass the performance achieved using hyperbolic tangent or sigmoid neurons, especially in deep networks. With rectified neurons we can readily create sparse representations, which seems especially suitable f...

Image classification is a popular and challenging topic in the computer vision field. On the basis of advances in neuroscience, this paper proposes a sparse-based neural response feature extraction method for image classification. The approach extracts discriminative and invariant representations of images by alternating between non-negative sparse coding and maximum pooling operation with effe...

Sparse representations using overcomplete dictionaries have proved to be a powerful tool in many signal processing applications such as denoising, super-resolution, inpainting, compression or classification. The sparsity of the representation very much depends on how well the dictionary is adapted to the data at hand. In this paper, we propose a method for learning structured multilevel diction...

In this thesis we study unsupervised learning algorithms for training feature extractors and building deep learning models. We propose sparse-modeling algorithms as the foundation for unsupervised feature extraction systems. To reduce the cost of the inference process required to obtain the optimal sparse code, we model a feed-forward function that is trained to predict this optimal sparse code...

Classification of various rice types and determination of its quality is a major issue in the scientific and commercial fields associated with modern agriculture. In recent years, various image processing techniques are used to identify different types of agricultural products. There are also various color and texture-based features in order to achieve the desired results in this area. In this ...