Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology
Researchers have developed a new algebraic framework for deep convolutional neural networks using lattice theory and mathematical morphology. This approach systematically analyzes standard network layers, revealing that the typical pipeline of linear convolution, ReLU, and max-pooling results in a cross-lattice operator. The study identifies three specific layer designs—max-plus morphological, spectral Wiener, and self-dual morphological—that function as genuine idempotent openings, offering a theoretical basis for the representational power gained through network depth. AI
IMPACT Provides a rigorous mathematical foundation for understanding and potentially designing more effective deep convolutional neural networks.