Publications by Angeliki Pantazi

High-performance deep spiking neural networks with 0.3 spikes per neuron

Wulfram Gerstner, Stanislaw Andrzej Wozniak, Ana Stanojevic, Angeliki Pantazi

Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that theoretical resul ...

Springer Science and Business Media LLC2024

An exact mapping from ReLU networks to spiking neural networks

Wulfram Gerstner, Stanislaw Andrzej Wozniak, Ana Stanojevic, Giovanni Cherubini, Angeliki Pantazi

Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propose an ...

2023

An exact mapping from ReLU networks to spiking neural networks' [Neural Networks(vol168, pg 74, 2023)

Wulfram Gerstner, Stanislaw Andrzej Wozniak, Ana Stanojevic, Giovanni Cherubini, Angeliki Pantazi

Pergamon-Elsevier Science Ltd2023

Approximating Relu Networks By Single-Spike Computation

Wulfram Gerstner, Stanislaw Andrzej Wozniak, Ana Stanojevic, Evangelos Eleftheriou, Giovanni Cherubini, Angeliki Pantazi

Developing energy-saving neural network models is a topic of rapidly increasing interest in the artificial intelligence community. Spiking neural networks (SNNs) are biologically inspired models that strive to leverage the energy efficiency stemming from a ...

IEEE2022

Neuromorphic System with Phase-Change Synapses for Pattern Learning and Feature Extraction

Yusuf Leblebici, Stanislaw Andrzej Wozniak, Evangelos Eleftheriou, Angeliki Pantazi

Neuromorphic systems provide biologically inspired methods of computing, alternative to the classical von Neumann approach. In these systems, computation is performed by a network of spiking neurons controlled by the values of their synaptic weights, which ...

2017

Neuromorphic Architecture with 1M Memristive Synapses for Detection of Weakly Correlated Inputs

Yusuf Leblebici, Stanislaw Andrzej Wozniak, Evangelos Eleftheriou, Severin Sidler, Angeliki Pantazi

Neuromorphic computing takes inspiration from the brain to build highly parallel, energy- and area-efficient architectures. Recently, hardware realizations of neurons and synapses using memristive devices were proposed and applied for the task of correlati ...

Ieee-Inst Electrical Electronics Engineers Inc2017

Unsupervised Learning Using Phase-Change Synapses and Complementary Patterns

Yusuf Leblebici, Stanislaw Andrzej Wozniak, Evangelos Eleftheriou, Severin Sidler, Angeliki Pantazi

Neuromorphic systems using memristive devices provide a brain-inspired alternative to the classical von Neumann processor architecture. In this work, a spiking neural network (SNN) implemented using phase-change synapses is studied. The network is equipped ...

2017

All-memristive neuromorphic computing with level-tuned neurons

Stanislaw Andrzej Wozniak, Evangelos Eleftheriou, Angeliki Pantazi

In the new era of cognitive computing, systems will be able to learn and interact with the environment in ways that will drastically enhance the capabilities of current processors, especially in extracting knowledge from vast amount of data obtained from m ...

Iop Publishing Ltd2016

Learning spatio-temporal patterns in the presence of input noise using phase-change memristors

Stanislaw Andrzej Wozniak, Evangelos Eleftheriou, Angeliki Pantazi

Neuromorphic systems increasingly attract research interest owing to their ability to provide biologically inspired methods of computing, alternative to the classic von Neumann architecture. In these systems, computing relies on spike-based communication b ...

2016