We are pleased to announce that the paper entitled " An Analog-Implemented Burst-Dependent Synaptic Plasticity Model for Hierarchical Neuromorphic Architectures " received the 2nd place Best Paper Award in the 37th International Conference on Microelectronics (ICM), which took place in Cairo Egypt from 14-17 December 2025.

The Award-Winning paper was co-authored by Vasileios Moustakas (PhD Student, ECE-NTUA and Researcher Archimedes/Athena RC), Dr. Vassilis Alimisis (Collaborating Researcher, ECE-NTUA and Postdoctoral Researcher Archimedes/Athena RC , Anna Mylona (Diploma Student, ECE- NTUA and Researcher Archimedes/Athena RC) , Francky Catthoor (Visiting Professor at ECE-NTUA, IMEC), and Paul P. Sotiriadis (Professor, ECE-NTUA; Lead Researcher, Archimedes/ Athena RC; IEEE, AIIA & AAIA Fellow ).

ABSTRACT: Synaptic plasticity utilizing only pre- and postsynaptic spike timing is proven to be unreliable for credit assignments in deep, hierarchical networks. Recent theoretical work shows that synaptic plasticity through high-frequency postsynaptic bursts enables higher-order neurons to coordinate learning in lower layers through feedback pathways. In this work, we present a low-power analog implemented burst-dependent synaptic plasticity (BDSP) architecture that captures these principles in hardware. The proposed design integrates a low-power, two-compartment neuron capable of event and burst generation with synapses that detect and quantify bursts, compute long-term burst probability, and use it to adjust weights. This architecture is designed and tested using Cadence IC suite in a TSMC 65nm CMOS process. Results showcase that the proposed design can be the cornerstone of an energy-efficiency neuromorphic hierarchical architecture.