18 citations · 50 across the 9 of their papers we have counts for
4 papers · 1 filter
Deconfounded Representation Similarity for Comparison of Neural Networks
Tianyu Cui, Yogesh Kumar, Pekka Marttinen +1
Similarity metrics such as representational similarity analysis (RSA) and centered kernel alignment (CKA) have been used to compare layer-wise representations between neural networ…
Informative Bayesian Neural Network Priors for Weak Signals
Tianyu Cui, Aki Havulinna, Pekka Marttinen +1
Encoding domain knowledge into the prior over the high-dimensional weight space of a neural network is challenging but essential in applications with limited data and weak signals.…
Multiple Output Regression with Latent Noise
Jussi Gillberg, Pekka Marttinen, Matti Pirinen +7
In high-dimensional data, structured noise caused by observed and unobserved factors affecting multiple target variables simultaneously, imposes a serious challenge for modeling, b…
Bayesian Information Sharing Between Noise And Regression Models Improves Prediction of Weak Effects
Jussi Gillberg, Pekka Marttinen, Matti Pirinen +5
We consider the prediction of weak effects in a multiple-output regression setup, when covariates are expected to explain a small amount, less than , of the variance of…