Non-uniqueness phenomenon of object representation in modelling IT cortex by deep convolutional neural network (DCNN)
This reveals a fundamental issue for researchers in computational neuroscience and AI modeling of vision, though it is incremental as it critiques an existing method.
The paper identifies a non-uniqueness problem in using deep convolutional neural networks (DCNNs) to model object representations in the primate inferotemporal cortex, highlighting theoretical limitations of this approach.
Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modelling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modelling of image object representations. This non-uniqueness phenomenon reveals to some extent the theoretical limitation of this general modelling approach, and invites due attention to be taken in practice.