20.500.12556/DKUM-94526 Prunability of multi-layer perceptrons trained with the forward-forward algorithm We explore the sparsity and prunability of multi-layer perceptrons (MLPs) trained using the Forward-Forward (FF) algorithm, an alternative to backpropagation (BP) that replaces the backward pass with local, contrastive updates at each layer. We analyze the sparsity of the weight matrices during training using multiple metrics, and test the prunability of FF networks on the MNIST, FashionMNIST and CIFAR-10 datasets. We also propose FFLib—a novel, modular PyTorch-based library for developing, training and analyzing FF models along with a suite of FF-based architectures, including FFNN, FFNN+C and FFRNN. In addition to structural sparsity, we describe and apply a new method for visualizing the functional sparsity of neural activations across different architectures using the HSV color space. Moreover, we conduct a sensitivity analysis to assess the impact of hyperparameters on model performance and sparsity. Finally, we perform pruning experiments, showing that simple FF-based MLPs exhibit significantly greater robustness to one-shot neuron pruning than traditional BP-trained networks, and a possible 8-fold increase in compression ratios while maintaining comparable accuracy on the MNIST dataset. Forward-Forward sparsity pruning model compression machine learning neural network nevronske mreže strojno učenje stiskanje modela razpršenost true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/mathematics © 2025 by the authors Članek v reviji 2025-08-20 12:14:02 2025-08-20 12:14:02 2025-08-21 03:09:43 0000-00-00 00:00:00 2025 0 0 23 str. iss. 16, [article no.] 2668 Vol. 13 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2025-06-22 2025-08-15 2025-08-19 004.9 246013187 10.3390/math13162668 2227-7390 mathematics-13-02668-v2.pdf mathematics-13-02668-v2.pdf 1 C04BE66BFE440B30671ECBB8D216ACF6 c6a4469d4bee386f8f6d79ba20281e6f05b7b3a1c9da4020b4f1f62acc5dce1d ac5ab024-7dae-11f0-a14c-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=195699 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0