Alexandros Iosifidis

Exploiting heterogeneity in operational neural networks by synaptic plasticity

2021 · Neural Computing and Applications

Abstract The recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs) that are homogenous only with a linear neuron model. As a heterogenous network model, ONNs are based …

On Feature Diversity in Energy-based Models

2023 · arXiv (Cornell University)

Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-model(s) that learn a combination of the different features to generate an energy …

Dynamic Semantic Compression for CNN Inference in Multi-Access Edge Computing: A Graph Reinforcement Learning-Based Autoencoder

2024 · IEEE Transactions on Wireless Communications

This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and edge servers’ available capacity, we propose a novel semantic compression method, …