arXiv subjects

Suman Datta

Publications and source records attributed to Suman Datta.

36 records · Page 2Linked to original sources

arXiv2022

2022 Roadmap on Neuromorphic Computing and Engineering

Modern computation based on the von Neumann architecture is today a mature cutting-edge science. In the Von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The Roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges. We hope that this Roadmap will be a useful resource to readers outside this field, for those who are just entering the field, and for those who are well established in the neuromorphic community. https://doi.org/10.1088/2634-4386/ac4a83

cs.ET↗

arXiv2021

Logic Compatible High-Performance Ferroelectric Transistor Memory

Silicon ferroelectric field-effect transistors (FeFETs) with low-k interfacial layer (IL) between ferroelectric gate stack and silicon channel suffers from high write voltage, limited write endurance and large read-after-write latency due to early IL breakdown and charge trapping and detrapping at the interface. We demonstrate low voltage, high speed memory operation with high write endurance using an IL-free back-end-of-line (BEOL) compatible FeFET. We fabricate IL-free FeFETs with 28nm channel length and 126nm width under a thermal budget <400C by integrating 5nm thick Hf0.5Zr0.5O2 gate stack with amorphous Indium Tungsten Oxide (IWO) semiconductor channel. We report 1.2V memory window and read current window of 10^5 for program and erase, write latency of 20ns with +/-2V write pulses, read-after-write latency <200ns, write endurance cycles exceeding 5x10^10 and 2-bit/cell programming capability. Array-level analysis establishes IL-free BEOL FeFET as a promising candidate for logic-compatible high-performance on-chip buffer memory and multi-bit weight cell for compute-in-memory accelerators.

cond-mat.mes-hall↗

arXiv2021

An Ising Hamiltonian Solver using Stochastic Phase-Transition Nano- Oscillators

Computationally hard problems, including combinatorial optimization, can be mapped into the problem of finding the ground-state of an Ising Hamiltonian. Building physical systems with collective computational ability and distributed parallel processing capability can accelerate the ground-state search. Here, we present a continuous-time dynamical system (CTDS) approach where the ground-state solution appears as stable points or attractor states of the CTDS. We harness the emergent dynamics of a network of phase-transition nano-oscillators (PTNO) to build an Ising Hamiltonian solver. The hardware fabric comprises of electrically coupled injection-locked stochastic PTNOs with bi-stable phases emulating artificial Ising spins. We demonstrate the ability of the stochastic PTNO-CTDS to progressively find more optimal solution by increasing the strength of the injection-locking signal - akin to performing classical annealing. We demonstrate in silico that the PTNO-CTDS prototype solves a benchmark non-deterministic polynomial time (NP)-hard Max-Cut problem with high probability of success. Using experimentally calibrated numerical simulations and incorporating non-idealities, we investigate the performance of our Ising Hamiltonian solver on dense Max-Cut problems with increasing graph size. We report a high energy-efficiency of 1.3x10^7 solutions/sec/Watt for 100-node dense Max-cut problems which translates to a 5x improvement over the recently demonstrated memristor-based Hopfield network and several orders of magnitude improvement over other candidates such as CPU and GPU, quantum annealer and photonic Ising solver approaches. Such an energy efficient hardware exhibiting high solution-throughput/Watt can find applications in industrial planning and manufacturing, defense and cyber-security, bioinformatics and drug discovery.

cond-mat.mes-hall↗

arXiv2021

Neural Sampling Machine with Stochastic Synapse allows Brain-like Learning and Inference

Many real-world mission-critical applications require continual online learning from noisy data and real-time decision making with a defined confidence level. Probabilistic models and stochastic neural networks can explicitly handle uncertainty in data and allow adaptive learning-on-the-fly, but their implementation in a low-power substrate remains a challenge. Here, we introduce a novel hardware fabric that implements a new class of stochastic NN called Neural-Sampling-Machine that exploits stochasticity in synaptic connections for approximate Bayesian inference. Harnessing the inherent non-linearities and stochasticity occurring at the atomic level in emerging materials and devices allows us to capture the synaptic stochasticity occurring at the molecular level in biological synapses. We experimentally demonstrate in-silico hybrid stochastic synapse by pairing a ferroelectric field-effect transistor -based analog weight cell with a two-terminal stochastic selector element. Such a stochastic synapse can be integrated within the well-established crossbar array architecture for compute-in-memory. We experimentally show that the inherent stochastic switching of the selector element between the insulator and metallic state introduces a multiplicative stochastic noise within the synapses of NSM that samples the conductance states of the FeFET, both during learning and inference. We perform network-level simulations to highlight the salient automatic weight normalization feature introduced by the stochastic synapses of the NSM that paves the way for continual online learning without any offline Batch Normalization. We also showcase the Bayesian inferencing capability introduced by the stochastic synapse during inference mode, thus accounting for uncertainty in data. We report 98.25%accuracy on standard image classification task as well as estimation of data uncertainty in rotated samples.

cond-mat.dis-nn↗

arXiv2020

Indium-Tin-Oxide Transistors with One Nanometer Thick Channel and Ferroelectric Gating

In this work, we demonstrate high performance indium-tin-oxide (ITO) transistors with the channel thickness down to 1 nm and ferroelectric Hf0.5Zr0.5O2 as gate dielectric. On-current of 0.243 A/mm is achieved on sub-micron gate-length ITO transistors with a channel thickness of 1 nm, while it increases to as high as 1.06 A/mm when the channel thickness increases to 2 nm. A raised source/drain structure with a thickness of 10 nm is employed, contributing to a low contact resistance of 0.15 Ωmm and a low contact resistivity of 1.1{\times}10-7 Ωcm2. The ITO transistor with a recessed channel and ferroelectric gating demonstrates several advantages over 2D semiconductor transistors and other thin film transistors, including large-area wafer-size nanometer thin film formation, low contact resistance and contact resistivity, atomic thin channel being immunity to short channel effects, large gate modulation of high carrier density by ferroelectric gating, high-quality gate dielectric and passivation formation, and a large bandgap for the low-power back-end-of-line (BEOL) CMOS application.

physics.app-ph↗

arXiv2020

A Hybrid FeMFET-CMOS Analog Synapse Circuit for Neural Network Training and Inference

An analog synapse circuit based on ferroelectric-metal field-effect transistors is proposed, that offers 6-bit weight precision. The circuit is comprised of volatile least significant bits (LSBs) used solely during training, and non-volatile most significant bits (MSBs) used for both training and inference. The design works at a 1.8V logic-compatible voltage, provides 10^10 endurance cycles, and requires only 250ps update pulses. A variant of LeNet trained with the proposed synapse achieves 98.2% accuracy on MNIST, which is only 0.4% lower than an ideal implementation of the same network with the same bit precision. Furthermore, the proposed synapse offers improvements of up to 26% in area, 44.8% in leakage power, 16.7% in LSB update pulse duration, and two orders of magnitude in endurance cycles, when compared to state-of-the-art hybrid synaptic circuits. Our proposed synapse can be extended to an 8-bit design, enabling a VGG-like network to achieve 88.8% accuracy on CIFAR-10 (only 0.8% lower than an ideal implementation of the same network).

cs.ET↗

arXiv2019

Inherent Weight Normalization in Stochastic Neural Networks

Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are sufficient operations for deep neural networks. We call such models Neural Sampling Machines (NSM). We find that the probability of activation of the NSM exhibits a self-normalizing property that mirrors Weight Normalization, a previously studied mechanism that fulfills many of the features of Batch Normalization in an online fashion. The normalization of activities during training speeds up convergence by preventing internal covariate shift caused by changes in the input distribution. The always-on stochasticity of the NSM confers the following advantages: the network is identical in the inference and learning phases, making the NSM suitable for online learning, it can exploit stochasticity inherent to a physical substrate such as analog non-volatile memories for in-memory computing, and it is suitable for Monte Carlo sampling, while requiring almost exclusively addition and comparison operations. We demonstrate NSMs on standard classification benchmarks (MNIST and CIFAR) and event-based classification benchmarks (N-MNIST and DVS Gestures). Our results show that NSMs perform comparably or better than conventional artificial neural networks with the same architecture.

cs.LG↗

arXiv2019

Design space exploration of Ferroelectric FET based Processing-in-Memory DNN Accelerator

In this letter, we quantify the impact of device limitations on the classification accuracy of an artificial neural network, where the synaptic weights are implemented in a Ferroelectric FET (FeFET) based in-memory processing architecture. We explore a design-space consisting of the resolution of the analog-to-digital converter, number of bits per FeFET cell, and the neural network depth. We show how the system architecture, training models and overparametrization can address some of the device limitations.

cs.ET↗

arXiv2019

Phase Field Modeling of Domain Dynamics and Polarization Accumulation in Ferroelectric HZO

In this work, we investigate the accumulative polarization (P) switching characteristics of ferroelectric (FE) thin films under the influence of sequential electric-field pulses. By developing a dynamic phase-field simulation framework based on time-dependent Landau-Ginzburg model, we analyze P excitation and relaxation characteristics in FE. In particular, we show that the domain-wall instability can cause different spontaneous P-excitation/relaxation behaviors that, in turn, can influence P switching dynamics for different pulse sequences. By assuming a local and global distribution of coercive field among the grains of an FE sample, we model the P-accumulation process in Hf0.4Zr0.6O2 (HZO) and its dependency on applied electric field and excitation/relaxation time. According to our analysis, domain-wall motion along with its instability under certain conditions plays a pivotal role in accumulative P-switching and the corresponding excitation and relaxation characteristics.

physics.app-ph↗

arXiv2018

AI based Safety System for Employees of Manufacturing Industries in Developing Countries

In this paper authors are going to present a Markov Decision Process (MDP) based algorithm in Industrial Internet of Things (IIoT) as a safety compliance layer for human in loop system. Though some industries are moving towards Industry 4.0 and attempting to automate the systems as much as possible by using robots, still human in loop systems are very common in developing countries like India. When ever there is a need for human machine interaction, there is a scope of health hazard. In this work we have developed a system for one such industry using MDP. The proposed algorithm used in this system learned the probability of state transition from experience as well as the system is adaptable to new changes by incorporating the concept of transfer learning. The system was evaluated on the data set obtained from 39 sensors connected to a computer numerically controlled (CNC) machine pushing data every second in a 24x7 scenario. The state changes are typically instructed by a human which subsequently lead to some intentional or unintentional mistakes and errors. The proposed system raises an alarm for the operator to warn which he may or may not overlook depending on his own perception about the present condition of the system. Repeated ignorance of the operator for a particular state transition warning guides the system to retrain the model. We observed 95.61% alarms raised by the said system are taken care of by the operator. 3.2% alarms are coming from the changes in the system which in turn used to retrain the model and 1.19% alarms are false alarms. We could not compute the error coming from the mistake performed by the human operator as there is no ground truth available for that.

cs.CY↗

arXiv2018

Stochastic IMT (insulator-metal-transition) neurons: An interplay of thermal and threshold noise at bifurcation

Artificial neural networks can harness stochasticity in multiple ways to enable a vast class of computationally powerful models. Electronic implementation of such stochastic networks is currently limited to addition of algorithmic noise to digital machines which is inherently inefficient; albeit recent efforts to harness physical noise in devices for stochasticity have shown promise. To succeed in fabricating electronic neuromorphic networks we need experimental evidence of devices with measurable and controllable stochasticity which is complemented with the development of reliable statistical models of such observed stochasticity. Current research literature has sparse evidence of the former and a complete lack of the latter. This motivates the current article where we demonstrate a stochastic neuron using an insulator-metal-transition (IMT) device, based on electrically induced phase-transition, in series with a tunable resistance. We show that an IMT neuron has dynamics similar to a piecewise linear FitzHugh-Nagumo (FHN) neuron and incorporates all characteristics of a spiking neuron in the device phenomena. We experimentally demonstrate spontaneous stochastic spiking along with electrically controllable firing probabilities using Vanadium Dioxide (VO$_2$) based IMT neurons which show a sigmoid-like transfer function. The stochastic spiking is explained by two noise sources - thermal noise and threshold fluctuations, which act as precursors of bifurcation. As such, the IMT neuron is modeled as an Ornstein-Uhlenbeck (OU) process with a fluctuating boundary resulting in transfer curves that closely match experiments. As one of the first comprehensive studies of a stochastic neuron hardware and its statistical properties, this article would enable efficient implementation of a large class of neuro-mimetic networks and algorithms.

cs.ET↗

arXiv2017

Vertex coloring of graphs via phase dynamics of coupled oscillatory networks

While Boolean logic has been the backbone of digital information processing, there are classes of computationally hard problems wherein this conventional paradigm is fundamentally inefficient. Vertex coloring of graphs, belonging to the class of combinatorial optimization represents such a problem; and is well studied for its wide spectrum of applications in data sciences, life sciences, social sciences and engineering and technology. This motivates alternate, and more efficient non-Boolean pathways to their solution. Here, we demonstrate a coupled relaxation oscillator based dynamical system that exploits the insulator-metal transition in vanadium dioxide (VO2), to efficiently solve the vertex coloring of graphs. By harnessing the natural analogue between optimization, pertinent to graph coloring solutions, and energy minimization processes in highly parallel, interconnected dynamical systems, we harness the physical manifestation of the latter process to approximate the optimal coloring of k-partite graphs. We further indicate a fundamental connection between the eigen properties of a linear dynamical system and the spectral algorithms that can solve approximate graph coloring. Our work not only elucidates a physics-based computing approach but also presents tantalizing opportunities for building customized analog co-processors for solving hard problems efficiently.

cs.ET↗

arXiv2016

Computing with Dynamical Systems Based on Insulator-Metal-Transition Oscillators

In this paper we review recent work on novel computing paradigms using coupled oscillatory dynamical systems. We explore systems of relaxation oscillators based on linear state transitioning devices, which switch between two discrete states with hysteresis. By harnessing the dynamics of complex, connected systems we embrace the philosophy of "let physics do the computing" and demonstrate how complex phase and frequency dynamics of such systems can be controlled, programmed and observed to solve computationally hard problems. Although our discussion in this paper is limited to Insulator-to-Metallic (IMT) state transition devices, the general philosophy of such computing paradigms can be translated to other mediums including optical systems. We present the necessary mathematical treatments necessary to understand the time evolution of these systems and demonstrate through recent experimental results the potential of such computational primitives.

cs.ET↗

arXiv2016

Revisiting the theory of ferroelectric negative capacitance

In this paper we revisit the theory of negative capacitance, in a (i) standalone ferroelectric, (ii) ferroelectric-dielectric, and (iii) ferroelectric-semiconductor series combination, and show that it is important to minimize the total Gibbs free energy of the combined system (and not just the free energy of the ferroelectric) to obtain the correct states. The theory is explained both analytically and using numerical simulation, for ferroelectric materials with first order and second order phase transitions. The exact conditions for different regimes of operation in terms of hysteresis and gain are derived for ferroelectric-dielectric combination. Finally the ferroelectric-semiconductor series combination is analyzed to gain insights into the possibility of realization of steep slope transistors in a hysteresis free manner.

cond-mat.mes-hall↗

arXiv2016

Graphene stabilization of two-dimensional gallium nitride

The spectrum of two-dimensional (2D) materials beyond graphene offers a remarkable platform to study new phenomena in condensed matter physics. Among these materials, layered hexagonal boron nitride (hBN), with its wide bandgap energy (~5.0-6.0 eV), has clearly established that 2D nitrides are key to advancing novel devices1. A gap, however, remains between the theoretical prediction of 2D nitrides beyond hBN and experimental realization of such structures. Here we demonstrate the synthesis of 2D gallium nitride (GaN) via a novel migration-enhanced encapsulated growth (MEEG) technique utilizing epitaxial graphene. We theoretically predict and experimentally validate that the atomic structure of 2D GaN grown via MEEG is notably different from reported theory. Moreover, we establish that graphene plays a critical role in stabilizing the direct-bandgap (nearly 5.0 eV), 2D buckled structure. Our results provide a foundation for discovery and stabilization of novel 2D nitrides that are difficult to prepare via traditional synthesis.

cond-mat.mtrl-sci↗

arXiv2015

Atomically Thin Resonant Tunnel Diodes built from Synthetic van der Waals Heterostructures

Vertical integration of two-dimensional van der Waals materials is predicted to lead to novel electronic and optical properties not found in the constituent layers. Here, we present the direct synthesis of two unique, atomically thin, multi-junction heterostructures by combining graphene with the monolayer transition-metal dichalocogenides: MoS2, MoSe2, and WSe2.The realization of MoS2-WSe2-Graphene and WSe2-MoSe2-Graphene heterostructures leads toresonant tunneling in an atomically thin stack with spectrally narrow room temperature negative differential resistance characteristics.

cond-mat.mtrl-sci↗

arXiv2014

Synchronization of pairwise-coupled, identical, relaxation oscillators based on metal-insulator phase transition devices: A Model Study

Computing with networks of synchronous oscillators has attracted wide-spread attention as novel materials and device topologies have enabled realization of compact, scalable and low-power coupled oscillatory systems. Of particular interest are compact and low-power relaxation oscillators that have been recently demonstrated using MIT (metal- insulator-transition) devices using properties of correlated oxides. This paper presents an analysis of the dynamics and synchronization of a system of two such identical coupled relaxation oscillators implemented with MIT devices. We focus on two implementations of the oscillator: (a) a D-D configuration where complementary MIT devices (D) are connected in series to provide oscillations and (b) a D-R configuration where it is composed of a resistor (R) in series with a voltage-triggered state changing MIT device (D). The MIT device acts like a hysteresis resistor with different resistances in the two different states. The synchronization dynamics of such a system has been analyzed with purely charge based coupling using a resistive (Rc) and a capacitive (Cc) element in parallel. It is shown that in a D-D configuration symmetric, identical and capacitively coupled relaxation oscillator system synchronizes to an anti-phase locking state, whereas when coupled resistively the system locks in phase. Further, we demonstrate that for certain range of values of Rc and Cc, a bistable system is possible which can have potential applications in associative computing. In D-R configuration, we demonstrate the existence of rich dynamics including non-monotonic flows and complex phase relationship governed by the ratios of the coupling impedance. Finally, the developed theoretical formulations have been shown to explain experimentally measured waveforms of such pairwise coupled relaxation oscillators.

nlin.CD↗

arXiv1999

Shift of Spectral Lines due to Dynamic Multiple Scattering and Screening Effect: Implications for Discordant Redshifts

The frequency shift of spectral lines from astronomical objects is most often explained by the Doppler Effect arising in relative motion and the broadening of a particular line is supposed to depend on the absolute temperature, pressure or the different line of sight velocities. The Wolf effect on the other hand deals with correlation induced spectral changes and explains both the broadening and shift of the spectral lines. In this framework a sufficient condition for redshift has been derived and when applicable the shift is shown to be larger than broadening. Under this condition of larger shift than broadening we find a critical source frequency below which no spectrum is analyzable for a particular medium. This gives rise to new type of screening effect which may play significant role both at laboratory scale as well as in the astronomical domain. We apply a simple interpretation of the discordant redshifts in galaxy-quasar associations.

astro-ph↗