arXiv subjects

Georgios Zervakis

Publications and source records attributed to Georgios Zervakis.

At least 19 recordsLinked to original sources

arXiv2026

Low-Power PLL-Based Clock Stabilization for Flexible IGZO AMS Systems

Flexible electronics (FE) platforms rely on analog and mixed-signal (AMS) circuits - biosensors, readout front-ends, and analog-to-digital converters - that dominate both functionality and energy consumption, making on-chip clock generation an essential yet power-critical function. Existing oscillator-based solutions suffer from unbounded process, voltage, and temperature (PVT) drift that degrades signal integrity, while alternative clock sources can consume up to 90% of the total system power budget, rendering them inapplicable to FE platforms and elevating clock generation to a primary power and energy-efficiency design constraint. This paper presents the first phase-locked loop (PLL) architecture designed for n-type-only amorphous indium-gallium-zinc oxide (a-IGZO) thin-film transistor (TFT) technology, addressing FE-specific constraints such as the absence of p-type devices, limited carrier mobility, and strong PVT variability. Rather than targeting high-precision frequency synthesis, the proposed design operates as a low-bandwidth temporal stabilizer: a free-running ring-oscillator-based voltage-controlled oscillator (VCO) is softly regulated by a minimal charge-pump feedback loop to bound long-term frequency drift without requiring a continuous high-quality external reference. The proposed PLL supports frequencies from 1 kHz to 300 kHz while occupying 0.0115-0.0233 mm2 and consuming 0.115-0.153 mW. Compared with prior oscillator-based FE clocking solutions, our architecture reduces power by more than 400x while achieving footprint reductions exceeding 1500x compared to flexible VCOs, and more than 390x with respect to ring-oscillator solutions. Validated across four representative published IGZO AMS systems, the proposed PLL achieves an rms period jitter of 2.24 ns and a long-term frequency accuracy within 1000 ppm, providing reference-anchored clock stability in FE platforms.

cs.AR↗

arXiv2026

Co-Optimization of Analog Kolmogorov-Arnold Networks for Low-Power Function Approximation in Flexible Electronics

Wearable devices and Internet of Things (IoT) sensors require on-sensor processing of biosignals and environmental data, including computationally demanding operations such as nonlinear activation functions for neural network inference, sensor calibration curves to map raw readings to physical units, and signal preprocessing functions like logarithmic compression and power operations for feature extraction. These functions exhibit significant complexity, often involving transcendental operations and multivariate dependencies that are costly to implement digitally. Analog function approximation provides a power-efficient alternative by performing these computations in the analog domain, thereby reducing the energy overhead associated with analog-to-digital conversion and subsequent digital processing. Flexible Electronics (FE) present a particularly attractive platform for wearable applications due to mechanical flexibility and low-cost fabrication, but impose strict constraints on circuit density and power consumption, making efficient analog implementations critical but challenging. This work introduces Analog Kolmogorov-Arnold Networks (AKANs), developed via hardware-software co-optimization, to approximate these complex multivariate functions accurately under hardware imperfections. Our method incorporates circuit-level error modeling during training and applies pruning at both software and hardware levels to reduce area and power. Validation across multiple benchmarks demonstrates that our proposed pruning methodology not only reduces hardware cost but can also improve approximation accuracy by regularizing spline parameters. Results show up to 55% area and 50% power savings, with average reductions of nearly 30% across datasets, highlighting AKANs as a robust and generalizable framework for low-power analog function approximation in FE.

cs.AR↗

arXiv2026

Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition

The paradigm shift towards local and on-device inference under stringent resource constraints is represented by the tiny machine learning (TinyML) domain. The primary goal of TinyML is to integrate intelligence into tiny, low-cost devices under strict resource, energy, and latency constraints. However, the ultra-resource-constrained nature of these devices can lead to increased inference execution time, which can be detrimental in latency critical applications. At the same time, TinyML applications are often associated with sensitive data. As such, latency optimization approaches that rely on training samples are infeasible when such data is unavailable, proprietary, or sensitive, highlighting a pressing need for optimization approaches that do not require access to the training dataset and can be applied directly to pre-trained models. Replacing costly multiplications with more hardware-efficient operations, such as shifts and additions, has been proposed as an effective method for reducing inference latency. However, post-training power-of-two (Po2) approaches are scarce and, in many cases, lead to unacceptable accuracy loss. In this work, we propose a framework that applies approximate matrix decomposition to a given CNN in order to optimize hardware implementations subject to strict constraints and without any need of re-training or fine-tuning steps. The genetic algorithm-driven framework explores different matrix decompositions and resulting multiplier-less CNN accelerator designs for FPGA targets. A comprehensive evaluation of different TinyML benchmarks demonstrates our framework's efficacy in generating latency-optimized implementations that satisfy strict accuracy and resource constraints, achieving an average 33% latency improvement with an average accuracy loss of 1.3% compared to typical systolic array-based FPGA accelerators.

cs.AR↗

arXiv2025

Bespoke Co-processor for Energy-Efficient Health Monitoring on RISC-V-based Flexible Wearables

Flexible electronics offer unique advantages for conformable, lightweight, and disposable healthcare wearables. However, their limited gate count, large feature sizes, and high static power consumption make on-body machine learning classification highly challenging. While existing bendable RISC-V systems provide compact solutions, they lack the energy efficiency required. We present a mechanically flexible RISC-V that integrates a bespoke multiply-accumulate co-processor with fixed coefficients to maximize energy efficiency and minimize latency. Our approach formulates a constrained programming problem to jointly determine co-processor constants and optimally map Multi-Layer Perceptron (MLP) inference operations, enabling compact, model-specific hardware by leveraging the low fabrication and non-recurring engineering costs of flexible technologies. Post-layout results demonstrate near-real-time performance across several healthcare datasets, with our circuits operating within the power budget of existing flexible batteries and occupying only 2.42 mm^2, offering a promising path toward accessible, sustainable, and conformable healthcare wearables. Our microprocessors achieve an average 2.35x speedup and 2.15x lower energy consumption compared to the state of the art.

cs.LG↗

arXiv2025

Design and Optimization of Mixed-Kernel Mixed-Signal SVMs for Flexible Electronics

Flexible Electronics (FE) have emerged as a promising alternative to silicon-based technologies, offering on-demand low-cost fabrication, conformality, and sustainability. However, their large feature sizes severely limit integration density, imposing strict area and power constraints, thus prohibiting the realization of Machine Learning (ML) circuits, which can significantly enhance the capabilities of relevant near-sensor applications. Support Vector Machines (SVMs) offer high accuracy in such applications at relatively low computational complexity, satisfying FE technologies' constraints. Existing SVM designs rely solely on linear or Radial Basis Function (RBF) kernels, forcing a trade-off between hardware costs and accuracy. Linear kernels, implemented digitally, minimize overhead but sacrifice performance, while the more accurate RBF kernels are prohibitively large in digital, and their analog realization contains inherent functional approximation. In this work, we propose the first mixed-kernel and mixed-signal SVM design in FE, which unifies the advantages of both implementations and balances the cost/accuracy trade-off. To that end, we introduce a co-optimization approach that trains our mixed-kernel SVMs and maps binary SVM classifiers to the appropriate kernel (linear/RBF) and domain (digital/analog), aiming to maximize accuracy whilst reducing the number of costly RBF classifiers. Our designs deliver 7.7% higher accuracy than state-of-the-art single-kernel linear SVMs, and reduce area and power by 108x and 17x on average compared to digital RBF implementations.

cs.AR↗

arXiv2025

Invited Paper: Feature-to-Classifier Co-Design for Mixed-Signal Smart Flexible Wearables for Healthcare at the Extreme Edge

Flexible Electronics (FE) offer a promising alternative to rigid silicon-based hardware for wearable healthcare devices, enabling lightweight, conformable, and low-cost systems. However, their limited integration density and large feature sizes impose strict area and power constraints, making ML-based healthcare systems-integrating analog frontend, feature extraction and classifier-particularly challenging. Existing FE solutions often neglect potential system-wide solutions and focus on the classifier, overlooking the substantial hardware cost of feature extraction and Analog-to-Digital Converters (ADCs)-both major contributors to area and power consumption. In this work, we present a holistic mixed-signal feature-to-classifier co-design framework for flexible smart wearable systems. To the best of our knowledge, we design the first analog feature extractors in FE, significantly reducing feature extraction cost. We further propose an hardware-aware NAS-inspired feature selection strategy within ML training, enabling efficient, application-specific designs. Our evaluation on healthcare benchmarks shows our approach delivers highly accurate, ultra-area-efficient flexible systems-ideal for disposable, low-power wearable monitoring.

eess.SP↗

arXiv2025

Support Vector Machines Classification on Bendable RISC-V

Flexible Electronics (FE) technology offers uniquecharacteristics in electronic manufacturing, providing ultra-low-cost, lightweight, and environmentally-friendly alternatives totraditional rigid electronics. These characteristics enable a rangeof applications that were previously constrained by the costand rigidity of conventional silicon technology. Machine learning (ML) is essential for enabling autonomous, real-time intelligenceon devices with smart sensing capabilities in everyday objects. However, the large feature sizes and high power consumption ofthe devices oppose a challenge in the realization of flexible ML applications. To address the above, we propose an open-source framework for developing ML co-processors for the Bendable RISC-V core. In addition, we present a custom ML accelerator architecture for Support Vector Machine (SVM), supporting both one-vs-one (OvO) and one-vs-rest (OvR) algorithms. Our ML accelerator adopts a generic, precision-scalable design, supporting 4-, 8-, and 16-bit weight representations. Experimental results demonstrate a 21x improvement in both inference execution time and energy efficiency, on average, highlighting its potential for low-power, flexible intelligence on the edge.

cs.AR↗

arXiv2025

Exploration of Low-Power Flexible Stress Monitoring Classifiers for Conformal Wearables

Conventional stress monitoring relies on episodic, symptom-focused interventions, missing the need for continuous, accessible, and cost-efficient solutions. State-of-the-art approaches use rigid, silicon-based wearables, which, though capable of multitasking, are not optimized for lightweight, flexible wear, limiting their practicality for continuous monitoring. In contrast, flexible electronics (FE) offer flexibility and low manufacturing costs, enabling real-time stress monitoring circuits. However, implementing complex circuits like machine learning (ML) classifiers in FE is challenging due to integration and power constraints. Previous research has explored flexible biosensors and ADCs, but classifier design for stress detection remains underexplored. This work presents the first comprehensive design space exploration of low-power, flexible stress classifiers. We cover various ML classifiers, feature selection, and neural simplification algorithms, with over 1200 flexible classifiers. To optimize hardware efficiency, fully customized circuits with low-precision arithmetic are designed in each case. Our exploration provides insights into designing real-time stress classifiers that offer higher accuracy than current methods, while being low-cost, conformable, and ensuring low power and compact size.

cs.LG↗

arXiv2025

Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation

Printed electronics offer a promising alternative for applications beyond silicon-based systems, requiring properties like flexibility, stretchability, conformality, and ultra-low fabrication costs. Despite the large feature sizes in printed electronics, printed neural networks have attracted attention for meeting target application requirements, though realizing complex circuits remains challenging. This work bridges the gap between classification accuracy and area efficiency in printed neural networks, covering the entire processing-near-sensor system design and co-optimization from the analog-to-digital interface-a major area and power bottleneck-to the digital classifier. We propose an automated framework for designing printed Ternary Neural Networks with arbitrary input precision, utilizing multi-objective optimization and holistic approximation. Our circuits outperform existing approximate printed neural networks by 17x in area and 59x in power on average, being the first to enable printed-battery-powered operation with under 5% accuracy loss while accounting for analog-to-digital interfacing costs.

eess.SP↗

arXiv2025

Computing with Printed and Flexible Electronics

Printed and flexible electronics (PFE) have emerged as the ubiquitous solution for application domains at the extreme edge, where the demands for low manufacturing and operational cost cannot be met by silicon-based computing. Built on mechanically flexible substrates, printed and flexible devices offer unparalleled advantages in terms of form factor, bio-compatibility and sustainability, making them ideal for emerging and uncharted applications, such as wearable healthcare products or fast-moving consumer goods. Their desirable attributes stem from specialized fabrication technologies, e.g., Pragmatic's FlexIC, where advancements like ultra-thin substrates and specialized printing methods expand their hardware efficiency, and enable penetration to previously unexplored application domains. In recent years, significant focus has been on machine learning (ML) circuits for resource-constrained on-sensor and near-sensor processing, both in the digital and analog domains, as they meet the requirements of target applications by PFE. Despite their advancements, challenges like reliability, device integration and efficient memory design are still prevalent in PFE, spawning several research efforts towards cross-layer optimization and co-design, whilst showing promise for advancing printed and flexible electronics to new domains.

cs.AR↗

arXiv2025

Carbon-Efficient 3D DNN Acceleration: Optimizing Performance and Sustainability

As Deep Neural Networks (DNNs) continue to drive advancements in artificial intelligence, the design of hardware accelerators faces growing concerns over embodied carbon footprint due to complex fabrication processes. 3D integration improves performance but introduces sustainability challenges, making carbon-aware optimization essential. In this work, we propose a carbon-efficient design methodology for 3D DNN accelerators, leveraging approximate computing and genetic algorithm-based design space exploration to optimize Carbon Delay Product (CDP). By integrating area-efficient approximate multipliers into Multiply-Accumulate (MAC) units, our approach effectively reduces silicon area and fabrication overhead while maintaining high computational accuracy. Experimental evaluations across three technology nodes (45nm, 14nm, and 7nm) show that our method reduces embodied carbon by up to 30% with negligible accuracy drop.

cs.AR↗

arXiv2025

Function Approximation Using Analog Building Blocks in Flexible Electronics

Function approximation is crucial in Flexible Electronics (FE), where applications demand efficient computational techniques within strict constraints on size, power, and performance. Devices like wearables and compact sensors are constrained by their limited physical dimensions and energy capacity, making traditional digital function approximation challenging and hardware-demanding. This paper addresses function approximation in FE by proposing a systematic and generic approach using a combination of Analog Building Blocks (ABBs) that perform basic mathematical operations such as addition, multiplication, and squaring. These ABBs serve as the foundation for constructing splines, which are then employed in the creation of Kolmogorov-Arnold Networks (KANs), improving the approximation. The analog realization of KAN offers a promising alternative to digital solutions, providing significant hardware benefits, particularly in terms of area and power consumption. Our design achieves a 125x reduction in area and a 10.59% power saving compared to a digital spline with 8-bit precision. Results also show that the analog design introduces an approximation error of up to 7.58% due to both the design and parasitic elements. Nevertheless, KANs are shown to be a viable candidate for function approximation in FE, with potential for further optimization to address the challenges of error reduction and hardware cost.

cs.AR↗

arXiv2025

Compact Yet Highly Accurate Printed Classifiers Using Sequential Support Vector Machine Circuits

Printed Electronics (PE) technology has emerged as a promising alternative to silicon-based computing. It offers attractive properties such as on-demand ultra-low-cost fabrication, mechanical flexibility, and conformality. However, PE are governed by large feature sizes, prohibiting the realization of complex printed Machine Learning (ML) classifiers. Leveraging PE's ultra-low non-recurring engineering and fabrication costs, designers can fully customize hardware to a specific ML model and dataset, significantly reducing circuit complexity. Despite significant advancements, state-of-the-art solutions achieve area efficiency at the expense of considerable accuracy loss. Our work mitigates this by designing area- and power-efficient printed ML classifiers with little to no accuracy degradation. Specifically, we introduce the first sequential Support Vector Machine (SVM) classifiers, exploiting the hardware efficiency of bespoke control and storage units and a single Multiply-Accumulate compute engine. Our SVMs yield on average 6x lower area and 4.6% higher accuracy compared to the printed state of the art.

cs.LG↗

arXiv2025

Late Breaking Results: Leveraging Approximate Computing for Carbon-Aware DNN Accelerators

The rapid growth of Machine Learning (ML) has increased demand for DNN hardware accelerators, but their embodied carbon footprint poses significant environmental challenges. This paper leverages approximate computing to design sustainable accelerators by minimizing the Carbon Delay Product (CDP). Using gate-level pruning and precision scaling, we generate area-aware approximate multipliers and optimize the accelerator design with a genetic algorithm. Results demonstrate reduced embodied carbon while meeting performance and accuracy requirements.

cs.AR↗

arXiv2025

Late Breaking Results: Energy-Efficient Printed Machine Learning Classifiers with Sequential SVMs

Printed Electronics (PE) provide a mechanically flexible and cost-effective solution for machine learning (ML) circuits, compared to silicon-based technologies. However, due to large feature sizes, printed classifiers are limited by high power, area, and energy overheads, which restricts the realization of battery-powered systems. In this work, we design sequential printed bespoke Support Vector Machine (SVM) circuits that adhere to the power constraints of existing printed batteries while minimizing energy consumption, thereby boosting battery life. Our results show 6.5x energy savings while maintaining higher accuracy compared to the state of the art.

cs.LG↗

arXiv2024

Leveraging Highly Approximated Multipliers in DNN Inference

In this work, we present a control variate approximation technique that enables the exploitation of highly approximate multipliers in Deep Neural Network (DNN) accelerators. Our approach does not require retraining and significantly decreases the induced error due to approximate multiplications, improving the overall inference accuracy. As a result, our approach enables satisfying tight accuracy loss constraints while boosting the power savings. Our experimental evaluation, across six different DNNs and several approximate multipliers, demonstrates the versatility of our approach and shows that compared to the accurate design, our control variate approximation achieves the same performance, 45% power reduction, and less than 1% average accuracy loss. Compared to the corresponding approximate designs without using our technique, our approach improves the accuracy by 1.9x on average.

cs.AR↗

arXiv2024

Sequential Printed MLP Circuits for Super TinyML Multi-Sensory Applications

Super-TinyML aims to optimize machine learning models for deployment on ultra-low-power application domains such as wearable technologies and implants. Such domains also require conformality, flexibility, and non-toxicity which traditional silicon-based systems cannot fulfill. Printed Electronics (PE) offers not only these characteristics, but also cost-effective and on-demand fabrication. However, Neural Networks (NN) with hundreds of features -- often necessary for target applications -- have not been feasible in PE because of its restrictions such as limited device count due to its large feature sizes. In contrast to the state of the art using fully parallel architectures and limited to smaller classifiers, in this work we implement a super-TinyML architecture for bespoke (application-specific) NNs that surpasses the previous limits of state of the art and enables NNs with large number of parameters. With the introduction of super-TinyML into PE technology, we address the area and power limitations through resource sharing with multi-cycle operation and neuron approximation. This enables, for the first time, the implementation of NNs with up to $35.9\times$ more features and $65.4\times$ more coefficients than the state of the art solutions.

cs.AR↗

arXiv2024

Reducing ADC Front-end Costs During Training of On-sensor Printed Multilayer Perceptrons

Printed electronics technology offers a cost-effectiveand fully-customizable solution to computational needs beyondthe capabilities of traditional silicon technologies, offering ad-vantages such as on-demand manufacturing and conformal, low-cost hardware. However, the low-resolution fabrication of printedelectronics, which results in large feature sizes, poses a challengefor integrating complex designs like those of machine learn-ing (ML) classification systems. Current literature optimizes onlythe Multilayer Perceptron (MLP) circuit within the classificationsystem, while the cost of analog-to-digital converters (ADCs)is overlooked. Printed applications frequently require on-sensorprocessing, yet while the digital classifier has been extensivelyoptimized, the analog-to-digital interfacing, specifically the ADCs,dominates the total area and energy consumption. In this work,we target digital printed MLP classifiers and we propose thedesign of customized ADCs per MLP's input which involvesminimizing the distinct represented numbers for each input,simplifying thus the ADC's circuitry. Incorporating this ADCoptimization in the MLP training, enables eliminating ADC levelsand the respective comparators, while still maintaining highclassification accuracy. Our approach achieves 11.2x lower ADCarea for less than 5% accuracy drop across varying MLPs.

cs.AR↗