activity
20212023
most citedContinual Prune-and-Select: Class-incremental learning with specialized subnetworks

17 citations · 33 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV2023

Continual learning for surface defect segmentation by subnetwork creation and selection

Aleksandr Dekhovich, Miguel A. Bessa

We introduce a new continual (or lifelong) learning algorithm called LDA-CP&S that performs segmentation tasks without undergoing catastrophic forgetting. The method is applied to…

cs.LG2023

iPINNs: Incremental learning for Physics-informed neural networks

Aleksandr Dekhovich, Marcel H. F. Sluiter, David M. J. Tax +1

Physics-informed neural networks (PINNs) have recently become a powerful tool for solving partial differential equations (PDEs). However, finding a set of neural network parameters…

math.NA2022★ 16 cited

Cooperative data-driven modeling

Aleksandr Dekhovich, O. Taylan Turan, Jiaxiang Yi +1

Data-driven modeling in mechanics is evolving rapidly based on recent machine learning advances, especially on artificial neural networks. As the field matures, new data and models…

cs.LG2022★ 17 cited

Continual Prune-and-Select: Class-incremental learning with specialized subnetworks

Aleksandr Dekhovich, David M. J. Tax, Marcel H. F. Sluiter +1

The human brain is capable of learning tasks sequentially mostly without forgetting. However, deep neural networks (DNNs) suffer from catastrophic forgetting when learning one task…

cs.LG2021

Neural network relief: a pruning algorithm based on neural activity

Aleksandr Dekhovich, David M. J. Tax, Marcel H. F. Sluiter +1

Current deep neural networks (DNNs) are overparameterized and use most of their neuronal connections during inference for each task. The human brain, however, developed specialized…