Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric. S...

Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric. Steering the spectral geometry of the learned representations substantially increased reverse predictivity with modest reductions in forward predictivity, yielding a 55% relative improvement in bidirectional predictivity.Source: arXiv cs.LGhttps://arxiv.org/abs/2608.18244#MachineLearning