Learned feature representations are biased by complexity, learning order, position, and more

arXiv:2405.05847v1 Announce Type: new
Abstract: Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means to understand or improve a system's computations. In this work, however, we explore surprising dissociations between representation and computation that may pose challenges for such efforts. We create datasets in which we attempt to match the computational role that different features play, while manipulating other properties of the features or the …

abstract arxiv complexity computation cs.cv cs.lg explore feature fields focus however key machine machine learning neuroscience representation representation learning type work