Searcharxiv⌕ Search

arXiv subjects

Suhas Kumar

Publications and source records attributed to Suhas Kumar.

At least 19 recordsLinked to original sources
arXiv2026

Incorruptible Neural Networks: Training Models that can Generalize to Large Internal Perturbations

Flat regions of the neural network loss landscape have long been hypothesized to correlate with better generalization properties. A closely related but distinct problem is training models that are robust to internal perturbations to their weights, which may be an important need for future low-power hardware platforms. In this paper, we explore the usage of two methods, sharpness-aware minimization (SAM) and random-weight perturbation (RWP), to find minima robust to a variety of random corruptions to weights. We consider the problem from two angles: generalization (how do we reduce the noise-robust generalization gap) and optimization (how do we maximize performance from optimizers when subject to strong perturbations). First, we establish, both theoretically and empirically, that an over-regularized RWP training objective is optimal for noise-robust generalization. For small-magnitude noise, we find that SAM's adversarial objective further improves performance over any RWP configuration, but performs poorly for large-magnitude noise. We link the cause of this to a vanishing-gradient effect, caused by unevenness in the loss landscape, affecting both SAM and RWP. Lastly, we demonstrate that dynamically adjusting the perturbation strength to match the evolution of the loss landscape improves optimizing for these perturbed objectives.

cs.LG↗
arXiv2025

Ovonic switches enable energy-efficient dendrite-like computing

Over the last decade, dendrites within individual biological neurons, which were previously thought to generally perform information pooling and networking, have now been shown to express complex temporal dynamics, Boolean-like logic, arithmetic, signal discrimination, and edge detection for image and sound recognition. Mimicking this rich functional density could offer a powerful primitive for neuromorphic computing, which has sought to replace the aging digital computing paradigms using biological inspirations. Here, using electrically driven Ovonic threshold switching in Sb-Te-doped GeSe, we demonstrate a single two-terminal component capable of self-sustained dynamics and universal Boolean logic, in addition to XOR operations (which is traditionally thought to require a network of active components). We then employ logic-driven dynamics in a single component to detect and estimate the gradients of edges in images, a task that otherwise requires elaborate circuits. A network of Ovonic switches exhibits properties of a half adder and a full adder, in addition to discriminative logic accommodating inhibitory and excitatory signals. We show that this computational primitive is not only seemingly simpler, but also offers many orders of magnitude improved energy efficiency compared to prevailing digital solutions. As such, this work paves the path for potentially emulating dendrites for efficient post-digital neuromorphic computing.

cs.ET↗
arXiv2025

Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses

Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, suffers from key limitations in both biological and hardware perspectives. These include backward error propagation by symmetric weights, non-local credit assignment, and frozen activity during backward passes. We propose Forward Target Propagation (FTP), a biologically plausible and computationally efficient alternative that replaces the backward pass with a second forward pass. FTP estimates layerwise targets using only feedforward computations, eliminating the need for symmetric feedback weights or learnable inverse functions, hence enabling modular and local learning. We evaluate FTP on fully connected networks, CNNs, and RNNs, demonstrating accuracies competitive with BP on MNIST, CIFAR10, and CIFAR100, as well as effective modeling of long-term dependencies in sequential tasks. Moreover, FTP outperforms BP under quantized low-precision and emerging hardware constraints while also demonstrating substantial efficiency gains over other biologically inspired methods such as target propagation variants and forward-only learning algorithms. With its minimal computational overhead, forward-only nature, and hardware compatibility, FTP provides a promising direction for energy-efficient on-device learning and neuromorphic computing.

cs.LG↗
arXiv2025

Resolving the Electron Plume within a Scanning Electron Microscope

Scanning electron microscopy (SEM), a century-old technique, is today a ubiquitous method of imaging the surface of nanostructures. However, most SEM detectors simply count the number of secondary electrons from a material of interest, and thereby overlook the rich material information contained within them. Here, by simple modifications to a standard SEM tool, we resolve the momentum and energy information of secondary electrons by directly imaging the electron plume generated by the electron beam of the SEM. Leveraging these spectroscopic imaging capabilities, our technique is able to image lateral electric fields across a prototypical silicon p-n junctions and to distinguish differently doped regions, even when buried beyond depths typically accessible by SEM. Intriguingly, the sub-surface sensitivity of this technique reveals unexpectedly strong surface band bending within nominally passivated semiconductor structures, providing useful insights for complex layered component designs, in which interfacial dynamics dictate device operation. These capabilities for non-invasive, multi-modal probing of complicated electronic components are crucial in today's electronic manufacturing but is largely inaccessible even with sophisticated techniques. These results show that seemingly simple SEM can be extended to probe complex and useful material properties.

cond-mat.mtrl-sci↗
arXiv2024

Energy Efficient Knapsack Optimization Using Probabilistic Memristor Crossbars

Constrained optimization underlies crucial societal problems (for instance, stock trading and bandwidth allocation), but is often computationally hard (complexity grows exponentially with problem size). The big-data era urgently demands low-latency and low-energy optimization at the edge, which cannot be handled by digital processors due to their non-parallel von Neumann architecture. Recent efforts using massively parallel hardware (such as memristor crossbars and quantum processors) employing annealing algorithms, while promising, have handled relatively easy and stable problems with sparse or binary representations (such as the max-cut or traveling salesman problems).However, most real-world applications embody three features, which are encoded in the knapsack problem, and cannot be handled by annealing algorithms - dense and non-binary representations, with destabilizing self-feedback. Here we demonstrate a post-digital-hardware-friendly randomized competitive Ising-inspired (RaCI) algorithm performing knapsack optimization, experimentally implemented on a foundry-manufactured CMOS-integrated probabilistic analog memristor crossbar. Our solution outperforms digital and quantum approaches by over 4 orders of magnitude in energy efficiency.

cs.ET↗
arXiv2023

Energy-based learning algorithms for analog computing: a comparative study

Energy-based learning algorithms have recently gained a surge of interest due to their compatibility with analog (post-digital) hardware. Existing algorithms include contrastive learning (CL), equilibrium propagation (EP) and coupled learning (CpL), all consisting in contrasting two states, and differing in the type of perturbation used to obtain the second state from the first one. However, these algorithms have never been explicitly compared on equal footing with same models and datasets, making it difficult to assess their scalability and decide which one to select in practice. In this work, we carry out a comparison of seven learning algorithms, namely CL and different variants of EP and CpL depending on the signs of the perturbations. Specifically, using these learning algorithms, we train deep convolutional Hopfield networks (DCHNs) on five vision tasks (MNIST, F-MNIST, SVHN, CIFAR-10 and CIFAR-100). We find that, while all algorithms yield comparable performance on MNIST, important differences in performance arise as the difficulty of the task increases. Our key findings reveal that negative perturbations are better than positive ones, and highlight the centered variant of EP (which uses two perturbations of opposite sign) as the best-performing algorithm. We also endorse these findings with theoretical arguments. Additionally, we establish new SOTA results with DCHNs on all five datasets, both in performance and speed. In particular, our DCHN simulations are 13.5 times faster with respect to Laborieux et al. (2021), which we achieve thanks to the use of a novel energy minimisation algorithm based on asynchronous updates, combined with reduced precision (16 bits).

cs.LG↗
arXiv2021

Improved Hopfield Network Optimization using Manufacturable Three-terminal Electronic Synapses

We describe via simulation novel optimization algorithms for a Hopfield neural network constructed using manufacturable three-terminal Silicon-Oxide-Nitride-Oxide-Silicon (SONOS) synaptic devices. We first present a computationally-light, memristor-based, highly accurate compact model for the SONOS. Using the compact model, we describe techniques of simulated annealing in Hopfield networks by exploiting imperfect problem definitions, current leakage, and the continuous tunability of the SONOS to enable transient chaotic group dynamics. We project improvements in energy consumption and latency for optimization relative to the best CPUs and GPUs by at least 4 orders of magnitude, and also exceeding the best projected memristor-based hardware; along with a 100-fold increase in error-resilient hardware size (i.e., problem size).

cond-mat.mtrl-sci↗
arXiv2021

Universal phase dynamics in VO2 switches revealed by ultrafast operando diffraction

Strongly correlated materials that exhibit an insulator-metal transition are key candidates in the search for new computing platforms. Understanding the pathways and timescales underlying the electrically-driven insulator-metal transition is crucial for uncovering the fundamental limits of device operation. Using stroboscopic electron diffraction, we perform synchronized time-resolved measurements of atomic motions and electronic transport in operating vanadium dioxide switches. We discover an electrically-triggered, isostructural state that forms transiently on microsecond timescales, stabilized by local heterogeneities and interfacial interactions between the equilibrium phases. This metastable phase bears striking similarity to that formed under photoexcitation within picoseconds, suggesting a universal transformation pathway across eight orders of magnitude of timescale. Our results establish a new route for uncovering non-equilibrium and metastable phases in correlated materials, and open avenues for engineering novel dynamical behavior in nanoelectronics.

cond-mat.mtrl-sci↗
arXiv2020

Size scaling, dynamics, and electro-thermal bifurcation of VO2 Mott oscillators

Traditional electronic devices are well-known to improve in speed and energy-efficiency as their dimensions are reduced to the nanoscale. However, this scaling behavior remains unclear for nonlinear dynamical circuit elements, such as Mott neuron-like spiking oscillators, which are of interest for bio-inspired computing. Here we show that shrinking micrometer-sized VO2 oscillators to sub-100 nm effective sizes, achieved using a nanogap cut in a metallic carbon nanotube (CNT) electrode, does not guarantee faster spiking. However, an additional heat source such as Joule heating from the CNT, in combination with small size and heat capacity (defined by the narrow volume of VO2 whose insulator-metal transition is triggered by the CNT), can increase the spiking frequency by ~1000x due to an electro-thermal bifurcation in the nonlinear dynamics. These results demonstrate that nonlinear dynamical switches operate in a complex phase space which can be controlled by careful electro-thermal design, offering new tuning parameters for designing future biomimetic electronics.

cond-mat.mtrl-sci↗
arXiv2019

Thermodynamic Computing

The hardware and software foundations laid in the first half of the 20th Century enabled the computing technologies that have transformed the world, but these foundations are now under siege. The current computing paradigm, which is the foundation of much of the current standards of living that we now enjoy, faces fundamental limitations that are evident from several perspectives. In terms of hardware, devices have become so small that we are struggling to eliminate the effects of thermodynamic fluctuations, which are unavoidable at the nanometer scale. In terms of software, our ability to imagine and program effective computational abstractions and implementations are clearly challenged in complex domains. In terms of systems, currently five percent of the power generated in the US is used to run computing systems - this astonishing figure is neither ecologically sustainable nor economically scalable. Economically, the cost of building next-generation semiconductor fabrication plants has soared past $10 billion. All of these difficulties - device scaling, software complexity, adaptability, energy consumption, and fabrication economics - indicate that the current computing paradigm has matured and that continued improvements along this path will be limited. If technological progress is to continue and corresponding social and economic benefits are to continue to accrue, computing must become much more capable, energy efficient, and affordable. We propose that progress in computing can continue under a united, physically grounded, computational paradigm centered on thermodynamics. Herein we propose a research agenda to extend these thermodynamic foundations into complex, non-equilibrium, self-organizing systems and apply them holistically to future computing systems that will harness nature's innate computational capacity. We call this type of computing "Thermodynamic Computing" or TC.

cs.CY↗
arXiv2019

Harnessing Intrinsic Noise in Memristor Hopfield Neural Networks for Combinatorial Optimization

We describe a hybrid analog-digital computing approach to solve important combinatorial optimization problems that leverages memristors (two-terminal nonvolatile memories). While previous memristor accelerators have had to minimize analog noise effects, we show that our optimization solver harnesses such noise as a computing resource. Here we describe a memristor-Hopfield Neural Network (mem-HNN) with massively parallel operations performed in a dense crossbar array. We provide experimental demonstrations solving NP-hard max-cut problems directly in analog crossbar arrays, and supplement this with experimentally-grounded simulations to explore scalability with problem size, providing the success probabilities, time and energy to solution, and interactions with intrinsic analog noise. Compared to fully digital approaches, and present-day quantum and optical accelerators, we forecast the mem-HNN to have over four orders of magnitude higher solution throughput per power consumption. This suggests substantially improved performance and scalability compared to current quantum annealing approaches, while operating at room temperature and taking advantage of existing CMOS technology augmented with emerging analog non-volatile memristors.

cs.ET↗
arXiv2019

Fast Spiking of a Mott VO2-Carbon Nanotube Composite Device

The recent surge of interest in brain-inspired computing and power-efficient electronics has dramatically bolstered development of computation and communication using neuron-like spiking signals. Devices that can produce rapid and energy-efficient spiking could significantly advance these applications. Here we demonstrate DC-current or voltage-driven periodic spiking with sub-20 ns pulse widths from a single device composed of a thin VO2 film with a metallic carbon nanotube as a nanoscale heater. Compared with VO2-only devices, adding the nanotube heater dramatically decreases the transient duration and pulse energy, and increases the spiking frequency, by up to three orders of magnitude. This is caused by heating and cooling of the VO2 across its insulator-metal transition being localized to a nanoscale conduction channel in an otherwise bulk medium. This result provides an important component of energy-efficient neuromorphic computing systems, and a lithography-free technique for power-scaling of electronic devices that operate via bulk mechanisms.

physics.app-ph↗
arXiv2017

Oxygen migration during resistance switching and failure of hafnium oxide memristors

While the recent establishment of the role of thermophoresis/diffusion-driven oxygen migration during resistance switching in metal oxide memristors provided critical insights required for memristor modeling, extended investigations of the role of oxygen migration during ageing and failure remain to be detailed. Such detailing will enable failure-tolerant design, which can lead to enhanced performance of memristor-based next-generation storage-class memory. Here we directly observed lateral oxygen migration using in-situ synchrotron x-ray absorption spectromicroscopy of HfOx memristors during initial resistance switching, wear over millions of switching cycles, and eventual failure, through which we determined potential physical causes of failure. Using this information, we reengineered devices to mitigate three failure mechanisms, and demonstrated an improvement in endurance of about three orders of magnitude.

cond-mat.mtrl-sci↗
arXiv2017

Spatially uniform resistance switching of low current, high endurance titanium-niobium-oxide memristors

We analyzed micrometer-scale titanium-niobium-oxide prototype memristors, which exhibited low write-power (<3 {\mu}W) and energy (<200 fJ/bit/{\mu}m2), low read-power (~nW), and high endurance (>millions of cycles). To understand their physico-chemical operating mechanisms, we performed in-operando synchrotron x-ray transmission nanoscale spectromicroscopy using an ultra-sensitive time-multiplexed technique. We observed only spatially uniform material changes during cell operation, in sharp contrast to the frequently detected formation of a localized conduction channel in transition-metal-oxide memristors. We also associated the response of assigned spectral features distinctly to non-volatile storage (resistance change) and writing of information (application of voltage and Joule heating). These results provide critical insights into high-performance memristors that will aid in device design, scaling and predictive circuit-modeling, all of which are essential for the widespread deployment of successful memristor applications.

cond-mat.mtrl-sci↗
arXiv2017

Conduction Channel Formation and Dissolution Due to Oxygen Thermophoresis/Diffusion in Hafnium Oxide Memristors

Transition metal oxide memristors, or resistive random-access memory (RRAM) switches, are under intense development for storage-class memory because of their favorable operating power, endurance, speed, and density. Their commercial deployment critically depends on predictive compact models based on understanding nanoscale physico-chemical forces, which remains elusive and controversial owing to the difficulties in directly observing atomic motions during resistive switching, Here, using scanning transmission synchrotron x-ray spectromicroscopy to study in-situ switching of hafnium oxide memristors, we directly observed the formation of a localized oxygen-deficiency-derived conductive channel surrounded by a low-conductivity ring of excess oxygen. Subsequent thermal annealing homogenized the segregated oxygen, resetting the cells towards their as-grown resistance state. We show that the formation and dissolution of the conduction channel are successfully modeled by radial thermophoresis and Fick diffusion of oxygen atoms driven by Joule heating. This confirmation and quantification of two opposing nanoscale radial forces that affect bipolar memristor switching are important components for any future physics-based compact model for the electronic switching of these devices.

cond-mat.mtrl-sci↗
arXiv2016

Smart packaging of electronics and integrated MEMS devices using LTCC

Low Temperature Cofired Ceramics (LTCC) has been a popular multi layer ceramic (MCM) packaging material for many electronic applications. The main advantage with LTCC would be its ability to embed a major part of the electronic circuit within itself, apart from its enhanced RF functionality as against many lossy materials used. The advantages of LTCC in terms of frequency response, cost, ease of fabrication, etc over many other packaging materials are presented. The applicability of LTCC as a packaging material, circuit mounting material, substrate material or a base material for micro devices is discussed. Switches and filters fabricated on LTCC as a substrate are presented and their enhanced functionality is shown. Planar switches and RF MEMS switches on LTCC are discussed with regard to their isolation, insertion losses, return losses, repeatability, quality factor, parasitic effects and frequency response. Concern is also shown to parameters like actuation voltages, actuation times and complexity of fabrication. The parameters studied with design and fabrication of filters is also discussed, like Q factor, dispersive effects, limits on frequencies, etc. Discussion is also done with regard to LTCC as a base material for MEMS sensors and actuators and the performance variables of the same. Fabrication process parameters are presented. The important issue of feasibility of integration with microelectronic integrated circuitry is discussed and its effects are shown.

cond-mat.mtrl-sci↗
arXiv2016

Direct Observation of Localized Radial Oxygen Migration in Functioning Tantalum Oxide Memristors

Oxygen migration in tantalum oxide, a promising next-generation storage material, is studied using in-operando x-ray absorption spectromicroscopy and is used to microphysically describe accelerated evolution of conduction channel and device failure. The resulting ring-like patterns of oxygen concentration are modeled using thermophoretic forces and Fick diffusion, establishing the critical role of temperature-activated oxygen migration that has been under question lately.

cond-mat.mtrl-sci↗