Comments on Sejnowski's "The unreasonable effectiveness of deep learning in artificial intelligence" [arXiv:2002.04806]
This is an incremental commentary addressing theoretical gaps in understanding deep learning effectiveness for researchers.
The paper critiques Sejnowski's 2020 work for not explaining why deep convolutional neural networks approximate many mappings, and instead analyzes the practical usage, training constraints, and application scope of these networks.
Terry Sejnowski's 2020 paper [arXiv:2002.04806] is entitled "The unreasonable effectiveness of deep learning in artificial intelligence". However, the paper doesn't attempt to answer the implied question of why Deep Convolutional Neural Networks (DCNNs) can approximate so many of the mappings that they have been trained to model. While there are detailed mathematical analyses, this short paper attempts to look at the issue differently, considering the way that these networks are used, the subset of these functions that can be achieved by training (starting from some location in the original function space), as well as the functions to which these networks will actually be applied.