Baptiste Wicht

Baptiste Wicht
Université de Fribourg · Department of Informatics

PhD In Computer Science

About

15
Publications
23,916
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
90
Citations

Publications

Publications (15)
Chapter
Full-text available
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...
Article
Full-text available
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...
Thesis
Full-text available
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...
Conference Paper
Full-text available
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...
Conference Paper
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Technical Report
Full-text available
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...
Article
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...

Network

Cited By

Projects

Projects (3)
Project
Develop an high-performance Matrix-Vector computation library. This library: Expression Template Library (ETL) has high-performance kernels and can make use of Intel MKL library as well as NVIDIA CUBLAS, CUDNN, CUFFT libraries to bring more performance for large computation.