5 papers
Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning
Salar Beigzad, Vansh Verma
We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and generalization…
Resource-efficient medical image classification for edge devices
Mahsa Lavaei, Zahra Abadi, Salar Beigzad +1
Medical image classification is a critical task in healthcare, enabling accurate and timely diagnosis. However, deploying deep learning models on resource-constrained edge devices…
NetworkFF: Unified Layer Optimization in Forward-Only Neural Networks
Salar Beigzad
The Forward-Forward algorithm eliminates backpropagation's memory constraints and biological implausibility through dual forward passes with positive and negative data. However, co…
Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task
Alireza Maleki, Mahsa Lavaei, Mohsen Bagheritabar +2
Deep learning techniques have proven highly effective in image classification, but their deployment in resourceconstrained environments remains challenging due to high computationa…
Saliency Assisted Quantization for Neural Networks
Elmira Mousa Rezabeyk, Salar Beigzad, Yasin Hamzavi +2
Deep learning methods have established a significant place in image classification. While prior research has focused on enhancing final outcomes, the opaque nature of the decision-…