Deep learning had a significant impact on diverse pattern recognition tasks in the recent
past. In this paper, we investigate its potential for keyword spotting in handwritten documents …

An effective simulation of the urban sprawl in an urban agglomeration is conducive to
making regional policies. Previous studies verified the effectiveness of the cellular-automata …

Many people try solving Sudoku puzzles every day. These puzzles are usually found in
newspapers, magazines and so on. Whenever a person is unable to solve a puzzle or is …

We consider the problem of perception-based constraint solving, where part of the problem
specification is provided indirectly through an image provided by a user. As a pedagogical …

To spot keywords on handwritten documents, we present a hybrid keyword spotting system,
based on features extracted with Convolutional Deep Belief Networks and using Dynamic …

Sudoku is a famous Japanese puzzle game. It helps to enhances our logical thinking. Most
of the people have a habit of solving sudoku puzzle in a daily routine. It consists of number …

Dans le cadre de cette thèse, nous proposons d'utiliser des méthodologies permettant
d'extraire automatiquement des caractéristiques importantes depuis des images. Nous nous …

For a long time, we have seen people being obsessed with Sudoku, and solving it might
take people hours while most of them are not able to solve them at all. It gathered peoples' …

Für diese Arbeit wurde eine Android Anwendung geschrieben, welche ein Bild von einem
Sudoku lösen kann. Hierfür wurde Bildverarbeitung genutzt, um zum einen das Sudokugitter …

Abstract Deep Learning Library (DLL) is a library for machine learning with deep neural
networks that focuses on speed. It supports feed-forward neural networks such as fully …