arXiv subjects

Shantanu Chakrabartty

Publications and source records attributed to Shantanu Chakrabartty.

28 records · Page 2Linked to original sources

arXiv2021

In-filter Computing For Designing Ultra-light Acoustic Pattern Recognizers

We present a novel in-filter computing framework that can be used for designing ultra-light acoustic classifiers for use in smart internet-of-things (IoTs). Unlike a conventional acoustic pattern recognizer, where the feature extraction and classification are designed independently, the proposed architecture integrates the convolution and nonlinear filtering operations directly into the kernels of a Support Vector Machine (SVM). The result of this integration is a template-based SVM whose memory and computational footprint (training and inference) is light enough to be implemented on an FPGA-based IoT platform. While the proposed in-filter computing framework is general enough, in this paper, we demonstrate this concept using a Cascade of Asymmetric Resonator with Inner Hair Cells (CAR-IHC) based acoustic feature extraction algorithm. The complete system has been optimized using time-multiplexing and parallel-pipeline techniques for a Xilinx Spartan 7 series Field Programmable Gate Array (FPGA). We show that the system can achieve robust classification performance on benchmark sound recognition tasks using only ~ 1.5k Look-Up Tables (LUTs) and ~ 2.8k Flip-Flops (FFs), a significant improvement over other approaches.

eess.AS↗

arXiv2021

Using growth transform dynamical systems for spatio-temporal data sonification

Sonification, or encoding information in meaningful audio signatures, has several advantages in augmenting or replacing traditional visualization methods for human-in-the-loop decision-making. Standard sonification methods reported in the literature involve either (i) using only a subset of the variables, or (ii) first solving a learning task on the data and then mapping the output to an audio waveform, which is utilized by the end-user to make a decision. This paper presents a novel framework for sonifying high-dimensional data using a complex growth transform dynamical system model where both the learning (or, more generally, optimization) and the sonification processes are integrated together. Our algorithm takes as input the data and optimization parameters underlying the learning or prediction task and combines it with the psychoacoustic parameters defined by the user. As a result, the proposed framework outputs binaural audio signatures that not only encode some statistical properties of the high-dimensional data but also reveal the underlying complexity of the optimization/learning process. Along with extensive experiments using synthetic datasets, we demonstrate the framework on sonifying Electro-encephalogram (EEG) data with the potential for detecting epileptic seizures in pediatric patients.

cs.SD↗

arXiv2021

An Adaptive Synaptic Array using Fowler-Nordheim Dynamic Analog Memory

In this paper we present a synaptic array that uses dynamical states to implement an analog memory for energy-efficient training of machine learning (ML) systems. Each of the analog memory elements is a micro-dynamical system that is driven by the physics of Fowler-Nordheim (FN) quantum tunneling, whereas the system level learning modulates the state trajectory of the memory ensembles towards the optimal solution. We show that the extrinsic energy required for modulation can be matched to the dynamics of learning and weight decay leading to a significant reduction in the energy-dissipated during ML training. With the energy-dissipation as low as 5 fJ per memory update and a programming resolution up to 14 bits, the proposed synapse array could be used to address the energy-efficiency imbalance between the training and the inference phases observed in artificial intelligence (AI) systems.

cs.NE↗

arXiv2020

Multiplierless and Sparse Machine Learning based on Margin Propagation Networks

The new generation of machine learning processors have evolved from multi-core and parallel architectures that were designed to efficiently implement matrix-vector-multiplications (MVMs). This is because at the fundamental level, neural network and machine learning operations extensively use MVM operations and hardware compilers exploit the inherent parallelism in MVM operations to achieve hardware acceleration on GPUs and FPGAs. However, many IoT and edge computing platforms require embedded ML devices close to the network in order to compensate for communication cost and latency. Hence a natural question to ask is whether MVM operations are even necessary to implement ML algorithms and whether simpler hardware primitives can be used to implement an ultra-energy-efficient ML processor/architecture. In this paper we propose an alternate hardware-software codesign of ML and neural network architectures where instead of using MVM operations and non-linear activation functions, the architecture only uses simple addition and thresholding operations to implement inference and learning. At the core of the proposed approach is margin-propagation (MP) based computation that maps multiplications into additions and additions into a dynamic rectifying-linear-unit (ReLU) operations. This mapping results in significant improvement in computational and hence energy cost. In this paper, we show how the MP network formulation can be applied for designing linear classifiers, shallow multi-layer perceptrons and support vector networks suitable fot IoT platforms and tiny ML applications. We show that these MP based classifiers give comparable results to that of their traditional counterparts for benchmark UCI datasets, with the added advantage of reduction in computational complexity enabling an improvement in energy efficiency.

cs.LG↗

arXiv2020

A Self-powered Analog Sensor-data-logging Device based on Fowler-Nordheim Dynamical Systems

Continuous, battery-free operation of sensor nodes requires ultra-low-power sensing and data-logging techniques. Here we report that by directly coupling a sensor/transducer signal into globally asymptotically stable monotonic dynamical systems based on Fowler-Nordheim quantum tunneling, one can achieve self-powered sensing at an energy budget that is currently unachievable using conventional energy harvesting methods. The proposed device uses a differential architecture to compensate for environmental variations and the device can retain sensed information for durations ranging from hours to days. With a theoretical operating energy budget less than 10 attojoules, we demonstrate that when integrated with a miniature piezoelectric transducer the proposed sensor-data-logger can measure cumulative "action" due to ambient mechanical acceleration without any additional external power.

physics.app-ph↗

arXiv2020

Resonant Machine Learning Based on Complex Growth Transform Dynamical Systems

Traditional energy-based learning models associate a single energy metric to each configuration of variables involved in the underlying optimization process. Such models associate the lowest energy state to the optimal configuration of variables under consideration, and are thus inherently dissipative. In this paper we propose an energy-efficient learning framework that exploits structural and functional similarities between a machine learning network and a general electrical network satisfying the Tellegen's theorem. In contrast to the standard energy-based models, the proposed formulation associates two energy components, namely, active and reactive energy to the network. This ensures that the network's active-power is dissipated only during the process of learning, whereas the reactive-power is maintained to be zero at all times. As a result, in steady-state, the learned parameters are stored and self-sustained by electrical resonance determined by the network's nodal inductances and capacitances. Based on this approach, this paper introduces three novel concepts: (a) A learning framework where the network's active-power dissipation is used as a regularization for a learning objective function that is subjected to zero total reactive-power constraint; (b) A dynamical system based on complex-domain, continuous-time growth transforms which optimizes the learning objective function and drives the network towards electrical resonance under steady-state operation; and (c) An annealing procedure that controls the trade-off between active-power dissipation and the speed of convergence. As a representative example, we show how the proposed framework can be used for designing resonant support vector machines (SVMs), where we show that the support-vectors correspond to an LC network with self-sustained oscillations.

cs.LG↗

arXiv2018

A Unified Perspective of Evolutionary Game Dynamics Using Generalized Growth Transforms

In this paper, we show that different types of evolutionary game dynamics are, in principle, special cases of a dynamical system model based on our previously reported framework of generalized growth transforms. The framework shows that different dynamics arise as a result of minimizing a population energy such that the population as a whole evolves to reach the most stable state. By introducing a population dependent time-constant in the generalized growth transform model, the proposed framework can be used to explain a vast repertoire of evolutionary dynamics, including some novel forms of game dynamics with non-linear payoffs.

cs.NE↗

arXiv2017

A Fowler-Nordheim Integrator can Track the Density of Prime Numbers

"Does there exist a naturally occurring counting device that might elucidate the hidden structure of prime numbers ?" is a question that has fascinated computer scientists and mathematical physicists for decades. While most recent research in this area have explored the role of the Riemann zeta-function in different formulations of statistical mechanics, condensed matter physics and quantum chaotic systems, the resulting devices (quantum or classical) have only existed in theory or the fabrication of the device has been found to be not scalable to large prime numbers. Here we report for the first time that any hypothetical prime number generator, to our knowledge, has to be a special case of a dynamical system that is governed by the physics of Fowler-Nordheim (FN) quantum-tunneling. In this paper we report how such a dynamical system can be implemented using a counting process that naturally arises from sequential FN tunneling and integration of electrons on a floating-gate (FG) device. The self-compensating physics of the FG device makes the operation reliable and repeatable even when tunneling-currents approach levels below 1 attoamperes. We report measured results from different variants of fabricated prototypes, each of which shows an excellent match with the asymptotic prime number statistics. We also report similarities between the spectral signatures produced by the FN device and the spectral statistics of a hypothetical prime number sequence generator. We believe that the proposed floating-gate device could have future implications in understanding the process that generates prime numbers with applications in security and authentication.

cs.CR↗

arXiv2017

Global Optimization based on Growth Transform Dynamical Model

Conservation principles like conservation of charge or energy provide a natural way to couple and constrain different physical variables. In this letter, we propose a dynamical system model that exploits these constraints for solving non-convex global optimization problems. Unlike the traditional simulated annealing or quantum annealing based global optimization techniques, the proposed method optimizes a target objective function by continuously evolving a driver functional over a conservation manifold using a generalized variant of growth transformations. As a result, the driver functional converges to a Dirac-delta function that is centered at the global optimum of the target objective function. We provide an outline of the proof of convergence for the dynamical system model and we demonstrate the application of the model for implementing linear-time and constant-time decentralized sorting algorithms.

math.OC↗

arXiv2017

Energy-dissipation Limits in Variance-based Computing

Variance-based logic (VBL) uses the fluctuations or the variance in the state of a particle or a physical quantity to represent different logic levels. In this letter we show that compared to the traditional bi-stable logic representation the variance-based representation can theoretically achieve a superior performance trade-off (in terms of energy dissipation and information capacity) when operating at fundamental limits imposed by thermal-noise. We show that for a bi-stable logic device the lower limit on energy dissipated per bit is 4.35KT/bit, whereas under similar operating conditions, a VBL device could achieve a lower limit of sub-KT/bit. These theoretical results are general enough to be applicable to different instantiations and variants of VBL ranging from digital processors based on energy-scavenging or to processors based on the emerging valleytronic devices.

cs.ET↗