Interpreting weight maps in terms of cognitive or clinical neuroscience: nonsense?

Linear machine learning models can be seen as providing two outputs: predictions and weight maps. The latter shows the relative contribution of the individual features to the model and has been heavily used in the neuroimaging community to infer conclusions about brain structure/function. There has however been a recent debate on whether weight maps can provide information about the neural signals leading to a significant classification/regression model [1]-[3]. The authors of [1] indeed suggest that weight maps provide a poor recovery of the input neural signal and lead to false positives. They further demonstrate that the amplitude of the weight does not reflect the amplitude of the signal difference in a feature. However, their examples are specific cases with low signalto-noise ratio (SNR). Here, we investigate the recovery of two widespread techniques, namely SVM [4] and sparse MKL [5] when varying the SNR, as well as the distribution of simulated neural signals.