
Baptiste WichtUniversity of Fribourg · Department of Informatics
Baptiste Wicht
PhD In Computer Science
About
15
Publications
30,691
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
112
Citations
Publications
Publications (15)
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-connected Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). Our main motivation for this work was to propose and evaluate novel software engineering strategie...
Deep Learning Library (DLL) is a new library for machine learning with deep neural networks that focuses on speed. It supports feed-forward neural networks such as fully-connected Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). It also has very comprehensive support for Restricted Boltzmann Machines (RBMs) and Convolutio...
In this thesis, we propose to use methodologies that automatically learn how to extract relevant features from images. We are especially interested in evaluating how these features compare against handcrafted features. More precisely, we are interested in the unsupervised training that is used for the Restricted Boltzmann Machine (RBM) and Convolut...
Although Graphics Processing Units (GPUs) seem to currently be the best platform to train machine learning models, most research laboratories are still only equipped with standard CPU systems. In this paper, we investigate multiple techniques to speedup the training of Restricted Boltzmann Machine (RBM) models and Convolutional RBM (CRBM) models on...
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 Time Warping for word scoring. Features are learned from word images, in an unsupervised manner, using a sliding window to extract horizontal patches. For two single writer his...
In this paper, we propose a method to detect and recognize a Sudoku puzzle on images taken from a mobile camera. The lines of the grid are detected with a Hough transform. The grid is then recomposed from the lines. The digits position are extracted from the grid and finally, each character is recognized using a Deep Belief Network (DBN). To test o...
Profile-Guided Optimization (PGO) is an excellent means to improve the
performance of a compiled program. Indeed, the execution path data it provides
helps the compiler to generate better code and better cacheline packing.
At the time of this writing, compilers only support instrumentation-based
PGO. This proved effective for optimizing programs. H...
Although there are a lot of optimized concurrent algorithms for lists, queues, stacks, hash tables and other common data structures, there are much fewer optimized concurrent Binary Search Trees implementations. This paper compares several concurrent implementations of Binary Search Tree. The implementations are also compared to a concurrent skip l...
Cojac's runtime analysis of code identifies risky arithmetical operations both in Java bytecode and in native binaries
This article discusses the question of numerical problems in programming, and focuses on the approach of using on-the-fly code instrumentation to uncover them at runtime. Two realizations are presented: a complete and stable soluti...