5 papers
AttnGen: Attention-Guided Saliency Learning for Interpretable Genomic Sequence Classification
Rayhaneh Shabani Nia, Ali Karkehabadi
Deep neural networks have achieved strong performance in genomic sequence classification; however, relating their predictions to biologically meaningful sequence patterns remains c…
SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation
Ali Karkehabadi, Jamshid Hassanpour, Houman Homayoun +1
Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meanin…
Applying Machine Learning Tools for Urban Resilience Against Floods
Mahla Ardebili Pour, Mohammad B. Ghiasi, Ali Karkehabadi
Floods are among the most prevalent and destructive natural disasters, often leading to severe social and economic impacts in urban areas due to the high concentration of assets an…
FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropagation
Ali Karkehabadi, Houman Homayoun, Avesta Sasan
The Forward-Forward Learning (FFL) algorithm is a recently proposed solution for training neural networks without needing memory-intensive backpropagation. During training, labels…
Optimizing Underwater IoT Routing with Multi-Criteria Decision Making and Uncertainty Weights
Ali Karkehabadi, Mitra Bakhshi, Seyed Behnam Razavian
Effective data routing is vital in the Internet of Things (IoT) paradigm, especially in underwater mobile sensor networks where inefficiency can lead to significant resource consum…