Practical machine learning for spatial data - Practical machine learning for spatial data - Training
|Date:||05.11.2019 9:00 - 06.11.2019 16:15|
|Location details:||The event is organised at the CSC Training Facilities located in the premises of CSC at Keilaranta 14, Espoo, Finland. The best way to reach us is by public transportation; more detailed travel tips are available.|
|lecturers:|| Mats Sjöberg |
|The fee covers all materials, lunches as well as morning and afternoon coffees.|
Payment can be made with electronic invoicing, credit card, or direct bank transfer. Note that for electronic invoicing you need the operator and e-invoicing address (OVT code) of your organization. Please also note that invoice reference is needed for electronic invoicing in your organization, so please have this available when registering.
This course gives a practical introduction to machine learning for spatial data. On the first day shallow machine learning models are used. The second day is for deep learning models, especially convolutional neural networks (CNN).
The course consists of lectures and hands-on exercises. For the exercises scikit-learn and Puhti will be used on the first day and keras and Puhti-AI on the second day.
After the course the participants should have the skills and knowledge needed to begin applying machine learning and deep learning for different tasks and utilizing the GPU resources available at CSC for training and deploying their own neural networks.
- Basics of geoinformatics
- Basics of Python. The course will include a fair amount of reading Python code, so you should be able to follow Python syntax. If you need to refresh your Python skills you can go through the materials of Helsinki University GeoPython course.
- Familiarity with HPC environment and very basic Linux commands: cd, ls, mv, cp, rm, chmod, less, tail, echo, mkdir, pwd. If you have not worked with Taito or similar system before, please attend also the Geocomputing in Puhti supercomputer course on 4.11.2019.
|9:00-10:15||Introduction to machine learning|
|10:30-12:00||Introduction to exercises, preparing spatial data for machine learning|
|13:00-14:30||Image segmentation using unsupervised machine learning algorithms. Using decision tree and random forest for solving classification and regression problems.|
|14:45-16:15||Establishing non-parametric models such as SVM model along with grid search implementation|
|9:00-10:30||Introduction to deep learning models, loss functions, activation functions, and optimizers|
|10:45-12:00||Establishing a fully connected neural network for classification of satellite images|
|13:00-14:30||Establishing a convolutional neural network (CNN) for land cover classification using satellite images|