3 papers
cs.LG2025
Training Deep Morphological Neural Networks as Universal Approximators
Konstantinos Fotopoulos, Petros Maragos
We investigate deep morphological neural networks (DMNNs), studying how changes in algebraic structure affect the expressivity and trainability of deep architectures. We show that…
cs.LG2025
Sparse Hybrid Linear-Morphological Networks
Konstantinos Fotopoulos, Christos Garoufis, Petros Maragos
We investigate hybrid linear-morphological networks. Recent studies highlight the inherent affinity of morphological layers to pruning, but also their difficulty in training. We pr…
cs.CV2024
TropNNC: Structured Neural Network Compression Using Tropical Geometry
Konstantinos Fotopoulos, Petros Maragos, Panagiotis Misiakos
We present TropNNC, a framework for compressing neural networks with linear and convolutional layers and ReLU activations using tropical geometry. By representing a network's outpu…