- High Performance Computing
- Machine Learning
- BioImage Analysis
- Best Practices for Software Development
- Database support for humanities
High Performance Computing
- using DCSR clusters when you're not able to perform your research and run computations on your local computer.
- harnessing the DCSR clusters (CPU and GPU)
- scaling your codes to larger clusters like CSCS
- All faculties
- Cristian Ruiz - HPC programming, code optimisation
- Emmanuel Jeanvoine - HPC programming (CPU and GPU), code optimisation
- Mainly HEC and GSE faculties
- Flavio Calvo - HPC/scientific programming, code optimisation, numerical schemes/algorithmic
- Margot Sirdey - HPC/scientific programming, code optimisation, numerical schemes/algorithmic
Using the clusters efficiently
Scientific computing & choice of optimised libraries
Profiling & code optimisation
Terms of support
- service mode: you submit a ticket to firstname.lastname@example.org (don't forget to start the subject with DCSR), we can help for few hours. The service is free.
- project mode: you have a more complex project that requires several days/weeks/months of work. The service is billed (see U1 costs in support column in the cost model)
Please send an email to email@example.com and put "DCSR HPC support request" in the subject.
Machine learning methods are nowadays used in a wide variety of scientific domains. For example,
- Unsupervised machine learning methods may be used as tools for data exploration and visualisation (dimension reduction and clustering),
- Supervised machine learning methods may be used as tools to make predictions: given an input data point, predict the output (classification or regression).
At the DCSR, we can help you with the following aspects of machine learning.
We can help you to understand how a particular machine learning method works and how it may be used in your research. Note that the DCSR gives a few short courses on machine learning; see https://www.unil.ch/ci/dcsr-en
We can help you to choose and apply the appropriate machine learning methods in your research. This may involve a pilote phase during which we develop together codes and run them on your laptop or on the UNIL clusters. Later on, we can also help you with the production phase.
More specifically, we can help you to find existing machine learning programs that would fit the aim of your analysis, install and run them on your laptop or on the UNIL clusters, and explain the meaning of their underlying option parameters. If no satisfactory machine learning program exists, we can help you to develop new algorithms and write codes that would fit the aim of your analysis.
We can help you to implement efficiently your machine learning pipeline on the UNIL clusters. More specifically, we can help you to install your codes on the UNIL clusters and to profile them in order to find the optimal setting (in terms of RAM, number of nodes and CPU/GPU).
Foster UNIL collaborations
We can help you to find appropriate experts at the UNIL to discuss with you about specific machine learning related problems. Note that the DCSR organises a ML Café every 4 months during which two researchers give short presentations on how they use machine learning in their work, followed by discussions. The presentations should be accessible to a broad audience that knows machine learning methods but does not necessarily know the specific scientific aspects of the works presented. In this way you will discover how machine learning tools are being used in various field of research. If you are interested in participating to this informal meeting, please send an email to firstname.lastname@example.org with subject: DCSR ML Café.
A few examples:
1. An experimental scientist would like to learn how to analyse his/her data on his/her laptop or on the UNIL clusters by using machine learning methods. We can help this researcher to find appropriate machine learning tools, to understand how they work and to use them on his/her laptop or on the UNIL clusters.
2. A data scientist would like to implement a machine learning pipeline (on his/her laptop or on the UNIL clusters) but he/she is not sure how to do it properly. We can help this researcher to find and apply appropriate machine learning methods.
3. A data scientist has implemented a machine learning pipeline (on his/her laptop or on the UNIL clusters) and would like to discuss about the methodology he/she used. We can help this researcher to check whether his/her approach is correct and we can also suggest alternative approaches.
4. A data scientist has implemented a machine learning pipeline on his/her laptop and would like to run it on the UNIL clusters (going from laptop to cluster). We can help this researcher to implement efficiently his/her pipeline on the UNIL clusters. This may involve the installation of softwares and the profiling of codes.
From a quick question or a quick opinion, to a long project conceived and structured together. Everything related to extracting information and data from your images can be discussed together.
Here are some of the main topics that we are usually asked about:
- Image pre-processing and enhancement
- Object detection and/or image segmentation
- Object tracking
- Quantifications (shape, dynamics, colocalization, and other properties)
- Clustering / classification of objects
- Visualization (rendering high-dimensional images, 3D images, etc.)
- Analytics (statistics of the extracted information).
Contact & Terms of support
- service mode: if you need quick help on a certain problem / if you need a suggestion, an information or similar - Submit a ticket to email@example.com with subject: Service - *name of your department* .
- project mode: if you have a more complex project that requires several weeks/months of work and you want to collaborate with us - Submit a ticket to firstname.lastname@example.org with subject: Project - *name of your department* .
Other contact: email@example.com with subject DCSR Image Analysis
Best Practices for Software Development
Database support for humanities
Arches est une plateforme open source pour la gestion des données issues du patrimoine culturel. La DCSR met à disposition des chercheurs de l'UNIL des instances locales d'Arches.