$C^*$-algebra Net: A New Approach Generalizing Neural Network Parameters to $C^*$-algebra. (arXiv:2206.09513v2 [stat.ML] UPDATED)

Web: http://arxiv.org/abs/2206.09513

We propose a new framework that generalizes the parameters of neural network
models to $C^*$-algebra-valued ones. $C^*$-algebra is a generalization of the
space of complex numbers. A typical example is the space of continuous
functions on a compact space. This generalization enables us to combine
multiple models continuously and use tools for functions such as regression and
integration. Consequently, we can learn features of data efficiently and adapt
the models to problems continuously. We apply our framework to practical
problems …

arxiv ml network neural neural network