Comparing MKL-DR with other multiview methods Comparing MKL-DR with other multiview methods

Unsupervised Multiple Kernel Learning, an algorithm that allows for dimensionality reduction and data fusion, could be expressed as a specific implementation of an autoencoder. In this project we will look into potential ways of replicating the MKL-DR scenario with autoencoders. This will ultimately result in autoencoders that also allow for data fusion and dimensional reduction.

Preferred skills: comfortable with Matlab; notions of machine learning.

References:

[1] Simidjievski N, Bodnar C, Tariq I, Scherer P, Andres Terre H, Shams Z, Jamnik M, Liò P. Variational Autoencoders for Cancer Data Integration: Design Principles and Computational Practice. Front Genet. 2019 Dec 11;10:1205.

[2] P. Zhang et al., "Multimodal fusion for sensor data using stacked autoencoders," 2015 IEEE Tenth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), Singapore, 2015, pp. 1-2, doi: 10.1109/ISSNIP.2015.7106972.