Machine learning

Machine learning

Machine Learning (ML) is concerned with the construction and study of algorithms that can learn and make predictions from data. NLeSC is actively involved in developing its expertise in this area. Examples of related tasks include (but are not limited to):

  • time series classification
  • unsupervised learning (clustering)
  • natural language processing
  • sentiment analysis
  • topic modeling

Time series classification using decision trees have been used for to classify bird behavior from GPS and accelerometer data. An annotation and classification tools have been developed which have boosted the bio-logging based research of ecologists. ML is widely used in our humanities projects, for example in sentiment analysis or topic modeling. At NLeSC we have experience with unsupervised learning techniques (clustering) particularly for large-scale analysis of protein sequences/structures. Various ML techniques have been developed and used in the  Digital humanities projects

Currently, knowledge and experience is build on deep learning methods for time series classification. The software used is MATLAB, WEKA,  scikit-learn and Gensim. Currently deep learning packages are being explored.

Source: Machine learning

Via: Google Alert for ML