HackMD
Practical machine learning with spatial data
This document: https://hackmd.io/@GeospatialCSC/GeoML
Slides
Exercise material
Computing environment: www.puhti.csc.fi
Schedule
Monday 7.11.
9:00-12:00
- Practicalities and Introduction
- Lecture 1: Introduction to machine learning
- Exercise 1: Image segmentation using k-means with scikit-learn
12.00-13:00 - Lunch break
13:00-16:15
- Lecture 2: Shallow machine learning models
- Lecture 3: Preparing spatial data for machine learning
- Exercise 2: Preparing vector data for regression
Tuesday 8.11.
9:00-12:00
- Exercise 3: Shallow regression with scikit-learn
- Exercise 4: Image classification using shallow classifiers, grid search with scikit-learn
- Lecture 4: Introduction to deep learning models
12.00-13:00 - Lunch break
13:00-16:15
- Lecture 5: Fully connected neural networks
- Lecture 6: Puhti GPUs and batch jobs
- Exercise 5: Fully connected regressor with keras
Wednesday 9.11.
9:00-12:00
- Exercise 6: Fully connected classifier with keras
- Lecture 7: Convolutional neural networks (CNN)
- Exercise 7: Data preparations for CNN
12.00-13:00 - Lunch break
13:00-16:00
- Exercise 8: CNN based image segmentation with keras
- Lecture 8: GIS software supporting machine learning for spatial data.
- Wrap-up and where to go from here
