Find in Library

An increasing number of emerging applications in data science and engineering are based on multidimensional and structurally rich data. The irregularities, however, of high-dimensional data often compromise the effectiveness of standard machine learning algorithms. We hereby propose the Rank-<inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> Feedforward Neural Network (FNN), a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters, thereby offering two core advantages compared to typical machine learning methods. First, it handles inputs as multilinear arrays, bypassing the need for vectorization, and can thus fully exploit the structural information along every data dimension. Moreover, the number of the model&#x2019;s trainable parameters is substantially reduced, making it very efficient for small sample setting problems. We establish the universal approximation and learnability properties of Rank-<inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> FNN, and we validate its performance on real-world hyperspectral datasets. Experimental evaluations show that Rank-<inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> FNN is a computationally inexpensive alternative of ordinary FNN that achieves state-of-the-art performance on higher-order tensor data.