Anastasios Tefas
YOU?
Author Swipe
View article: A 262 TOPS hyperdimensional photonic AI accelerator powered by a Si3N4 microcomb laser
A 262 TOPS hyperdimensional photonic AI accelerator powered by a Si3N4 microcomb laser Open
The ever-increasing volume of data demarcating from the exponential scale of Artificial Intelligence (AI) and Deep Learning (DL) models motivated research into specialized AI accelerators in order to complement digital processors. Photonic…
View article: Time-space-wavelength multiplexed photonic tensor core using WDM SiGe EAM array chiplets
Time-space-wavelength multiplexed photonic tensor core using WDM SiGe EAM array chiplets Open
Photonic neural networks (PNNs) are projected to be the next-generation AI platform, driving significant advances in compute energy and area efficiency by leveraging light’s parallelism across space, wavelength, and time. Here we present a…
View article: Software Engineering for Self-Adaptive Robotics: A Research Agenda
Software Engineering for Self-Adaptive Robotics: A Research Agenda Open
Self-adaptive robotic systems operate autonomously in dynamic and uncertain environments, requiring robust real-time monitoring and adaptive behaviour. Unlike traditional robotic software with predefined logic, self-adaptive robots exploit…
View article: Comparison of ChatGPT-3.5 and GPT-4 as potential tools in artificial intelligence-assisted clinical practice in renal and liver transplantation
Comparison of ChatGPT-3.5 and GPT-4 as potential tools in artificial intelligence-assisted clinical practice in renal and liver transplantation Open
BACKGROUND Kidney and liver transplantation are two sub-specialized medical disciplines, with transplant professionals spending decades in training. While artificial intelligence-based (AI-based) tools could potentially assist in everyday …
View article: A 262 TOPS Hyperdimensional Photonic AI Accelerator powered by a Si3N4 microcomb laser
A 262 TOPS Hyperdimensional Photonic AI Accelerator powered by a Si3N4 microcomb laser Open
The ever-increasing volume of data has necessitated a new computing paradigm, embodied through Artificial Intelligence (AI) and Large Language Models (LLMs). Digital electronic AI computing systems, however, are gradually reaching their ph…
View article: New gravitational wave discoveries enabled by machine learning
New gravitational wave discoveries enabled by machine learning Open
The detection of gravitational waves (GWs) has revolutionized our understanding of the Universe, offering unprecedented insights into its dynamics. A major goal of GW data analysis is to speed up the detection and parameter estimation proc…
View article: Large Models in Dialogue for Active Perception and Anomaly Detection
Large Models in Dialogue for Active Perception and Anomaly Detection Open
Autonomous aerial monitoring is an important task aimed at gathering information from areas that may not be easily accessible by humans. At the same time, this task often requires recognizing anomalies from a significant distance or not pr…
View article: Reaching the Peta-Computing: 163.8 TOPS Through Multidimensional AWGR-Based Accelerators
Reaching the Peta-Computing: 163.8 TOPS Through Multidimensional AWGR-Based Accelerators Open
The prowess of Artificial Intelligence (AI) and Large Language Models (LLMs) to compute the exponentially growing data, coupled with the digital electronic AI computing systems reaching their physical plateaus, have stimulated extensive re…
View article: Using Part-based Representations for Explainable Deep Reinforcement Learning
Using Part-based Representations for Explainable Deep Reinforcement Learning Open
Utilizing deep learning models to learn part-based representations holds significant potential for interpretable-by-design approaches, as these models incorporate latent causes obtained from feature representations through simple addition.…
View article: UAV Active Perception and Motion Control for Improving Navigation Using Low-Cost Sensors
UAV Active Perception and Motion Control for Improving Navigation Using Low-Cost Sensors Open
In this study a model pipeline is proposed that combines computer vision with control-theoretic methods and utilizes low cost sensors. The proposed work enables perception-aware motion control for a quadrotor UAV to detect and navigate to …
View article: New Gravitational Wave Discoveries Enabled by Machine Learning
New Gravitational Wave Discoveries Enabled by Machine Learning Open
The detection of gravitational waves has revolutionized our understanding of the universe, offering unprecedented insights into its dynamics. A major goal of gravitational wave data analysis is to speed up the detection and parameter estim…
View article: Photonic neural networks and optics-informed deep learning fundamentals
Photonic neural networks and optics-informed deep learning fundamentals Open
The recent explosive compute growth, mainly fueled by the boost of artificial intelligence (AI) and deep neural networks (DNNs), is currently instigating the demand for a novel computing paradigm that can overcome the insurmountable barrie…
View article: Optics-informed Neural Networks: Bridging Deep Learning with Photonic Accelerators
Optics-informed Neural Networks: Bridging Deep Learning with Photonic Accelerators Open
We discuss our work in optics informed photonic neural networks, an architectural framework bridging the idiosyncrasy of integrated photonic architectures with a set of Deep Learning algorithms, towards harnessing the full potential of lig…
View article: Robotic safe adaptation in unprecedented situations: the RoboSAPIENS project
Robotic safe adaptation in unprecedented situations: the RoboSAPIENS project Open
The robots of tomorrow should be endowed with the ability to adapt to drastic and unpredicted changes in their environment and interactions with humans. Such adaptations, however, cannot be boundless: the robot must stay trustworthy. So, t…
View article: Deep Active Perception for Object Detection using Navigation Proposals
Deep Active Perception for Object Detection using Navigation Proposals Open
Deep Learning (DL) has brought significant advances to robotics vision tasks. However, most existing DL methods have a major shortcoming, they rely on a static inference paradigm inherent in traditional computer vision pipelines. On the ot…
View article: Photonic Neural Networks and Optics-informed Deep Learning Fundamentals
Photonic Neural Networks and Optics-informed Deep Learning Fundamentals Open
The recent explosive compute growth, mainly fueled by the boost of AI and DNNs, is currently instigating the demand for a novel computing paradigm that can overcome the insurmountable barriers imposed by conventional electronic computing a…
View article: Non-negative isomorphic neural networks for photonic neuromorphic accelerators
Non-negative isomorphic neural networks for photonic neuromorphic accelerators Open
Neuromorphic photonic accelerators are becoming increasingly popular, since they can significantly improve computation speed and energy efficiency, leading to femtojoule per MAC efficiency. However, deploying existing DL models on such pla…
View article: Mixed-precision quantization-aware training for photonic neural networks
Mixed-precision quantization-aware training for photonic neural networks Open
The energy demanding nature of deep learning (DL) has fueled the immense attention for neuromorphic architectures due to their ability to operate in a very high frequencies in a very low energy consumption. To this end, neuromorphic photon…
View article: Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Management
Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Management Open
Financial portfolio management describes the task of distributing funds and conducting trading operations on a set of financial assets, such as stocks, index funds, foreign exchange or cryptocurrencies, aiming to maximize the profit while …
View article: Multiplicative update rules for accelerating deep learning training and increasing robustness
Multiplicative update rules for accelerating deep learning training and increasing robustness Open
Even nowadays, where Deep Learning (DL) has achieved state-of-the-art performance in a wide range of research domains, accelerating training and building robust DL models remains a challenging task. To this end, generations of researchers …
View article: Deep Learning for Energy Time-Series Analysis and Forecasting
Deep Learning for Energy Time-Series Analysis and Forecasting Open
Energy time-series analysis describes the process of analyzing past energy observations and possibly external factors so as to predict the future. Different tasks are involved in the general field of energy time-series analysis and forecas…
View article: High-performance end-to-end deep learning IM/DD link using optics-informed neural networks
High-performance end-to-end deep learning IM/DD link using optics-informed neural networks Open
In this paper, we introduce optics-informed Neural Networks and demonstrate experimentally how they can improve performance of End-to-End deep learning models for IM/DD optical transmission links. Optics-informed or optics-inspired NNs are…