Vivek Saraswat

Graduate Student, Electrical Engineering

Indian Institute of Technology, Bombay

Prime Minister Research Fellow since May 2018

May 2022 Review Cycle: Recommended with Commendation

Curriculum Vitae

Contact Information:

4th floor, Nanoelectronics Building

Department of Electrical Engineering

IIT Bombay, Mumbai - 400076

Email - svivek@iitb.ac.in

Academic Background:

B. Tech + M. Tech Dual Degree in Electrical Engineering, IIT Bombay (Completed June 2018)
Minors in Computer Science

Research Interests:

Memory Devices (RRAM) Modelling and Simulation - Devices, Architectures and Variability
Neuromorphic Systems and Engineering - Liquid State Machines, Oscillator Networks

Advisor Information:

Prof. Udayan Ganguly

Address:

Department of Electrical Engineering, IIT Bombay, Powai, Mumbai 400 076, India, Office Room No: NanoE 605

Areas: Memories - Resistance RAM, Charge Trap / Nanocrystal Flash Memory, Ferroelectric RAM Logic - Transistor variability, SOI-MOSFETs Architecture: Neuromorphic Algorithms and Circuit Implementations

Phone (O): +91-22-2576-7698

E-Mail: udayan[AT]ee.iitb.ac.in

Course done during PhD:

EE 618 - CMOS Analog VLSI Design
EE 774 - Computational Techniques in Electrical Engineering
EES801 - Seminar
HS 791 - Communication Skills -I
EE 613 - Nonlinear Dynamical Systems
EE 620 - Physics of Transistors

Teaching Assistantship Experience:

IIT Bombay: VLSI Technology, Electronic Devices and Circuits, Solid State Devices, Nanoelectronics, Physics of Transistors, Neuromorphic Engineering (Awarded excellence in teaching assistantship four times)
IIT-BHU Varanasi (PMRF deliverable): Advanced Field Effect Devices (Certificate of TA duties completion Spring 2020-21), Micro-electronics (Certificate Autumn 2021-22)
IIT Gandhinagar (PMRF deliverable): Introduction to Neuromorphic Engineering (Guest Lectures, Spring 2021-22)

Project Information:

Emerging Non-volatile Memories are crucial for high density storage and in-memory computations to push semiconductor electronics industry beyond the scaling limits and memory walls. Resistive Random Access Memory or RRAM is a promising resistive switching memory (memristor) in this category. RRAM is appealing due to its simple metal-insulator-metal structure and electrical operation. Understanding the physics and modelling the RRAM devices to capture the static and dynamic behaviors of these devices is crucial to evaluate the performance at the circuits/systems level.

Specifically in this project, heavy transition metal compound oxides based RRAMs are modelled to capture the behavior and the physics. From an applications point of view, memristors are used as neurons, synapses in neuromorphic computing and computational cross-bar arrays in in-memory computing architectures. Further intrinsic stochasticity in RRAM device operation expands the application base to stochastic optimization networks like Boltzmann Machines and Oscillatory Neural Networks.

List of Publications:

Journals:

O. Phadke*, V. Saraswat*, and U. Ganguly, “Highly Deterministic One-Shot Set–Reset Programming Scheme in PCMO Resistive Random-Access Memory,” ACS Appl. Electron. Mater., p. acsaelm.2c00918, Sep. 2022, doi: 10.1021/acsaelm.2c00918.
A. K. Singh, V. Saraswat, M. S. Baghini, and U. Ganguly, “Quantum Tunneling Based Ultra-Compact and Energy Efficient Spiking Neuron Enables Hardware SNN,” IEEE Trans. Circuits Syst. I, pp. 1–13, 2022, doi: 10.1109/TCSI.2022.3172176.
V. Saraswat, U. Ganguly, “Stochasticity Invariance Control in Pr1−xCaxMnO3 RRAM to enable Large-Scale Stochastic Recurrent Neural Networks” (https://doi.org/10.1088/2634-4386/ac408a, Accepted at Neuromorphic Computing and Engineering, IOPScience, Dec, 2021)
O. Phadke, J. Sakhuja, V. Saraswat, and U. Ganguly, “Exploiting the electrothermal timescale in PrMnO 3 RRAM for a compact, clock-less neuron exhibiting biological spiking patterns,” Semicond. Sci. Technol., vol. 36, no. 11, p. 114001, Nov. 2021, doi: 10.1088/1361-6641/ac24e8.
V. Saraswat et al., “Reaction-Drift Model for Switching Transients in Pr₀.₇Ca₀.₃MnO₃-Based Resistive RAM,” IEEE Transactions on Electron Devices, vol. 67, no. 9, pp. 3610–3617, Sep. 2020, doi: 10.1109/TED.2020.3011387.
S. Lashkare, V. Saraswat, and U. Ganguly, “Understanding the Region of Resistance Change in Pr 0.7 Ca 0.3 MnO 3 RRAM,” ACS Applied Electronic Materials, vol. 2, no. 7, pp. 2026–2031, Jul. 2020, doi: 10.1021/acsaelm.0c00297.
D. Khilwani, V. Moghe, S. Lashkare, V. Saraswat, P. Kumbhare, M. Shojaei Baghini, S. Jandhyala, S. Subramoney, and U. Ganguly, “PrxCa1−xMnO3 based stochastic neuron for Boltzmann machine to solve ‘maximum cut’ problem,” APL Materials, vol. 7, no. 9, p. 091112, Sep. 2019, doi: 10.1063/1.5108694.
S. Lashkare, P. Kumbhare, V. Saraswat, and U. Ganguly, “Transient Joule Heating-Based Oscillator Neuron for Neuromorphic Computing,” IEEE Electron Device Letters, vol. 39, no. 9, pp. 1437–1440, Sep. 2018, doi: 10.1109/LED.2018.2854732.

Conferences:

S. Deshmukh, V. Saraswat, V. Gopinath, R. Nair, L. Somappa, M. Shojaei Baghini, and U. Ganguly, “ANN Inference enabled by Variability Mitigation using 2T-1R Bit Cell-based Design Space Analysis,” IEEE International Symposium on Circuits and Systems – ISCAS, Monterey, USA, May 2023 (Accepted)
R. Patel, V. Saraswat, and U. Ganguly, “Liquid State Machine on Loihi: Memory Metric for Performance Prediction,” in Artificial Neural Networks and Machine Learning – ICANN 2022, vol. 13531, E. Pimenidis, P. Angelov, C. Jayne, A. Papaleonidas, and M. Aydin, Eds. Cham: Springer Nature Switzerland, 2022, pp. 692–703. doi: 10.1007/978-3-031-15934-3_57.
O. Phadke, A. De, J. Sakhuja, V. Saraswat, and U. Ganguly, “Experimentally Validated Pr 0.7 Ca 0.3 MnO 3 RRAM Verilog-A model based Izhikevich Neuronal Dynamics,” in 2021 International Conference on Simulation of Semiconductor Processes and Devices (SISPAD), Dallas, TX, USA, Sep. 2021, pp. 280–284. doi: 10.1109/SISPAD54002.2021.9592590.
V. Saraswat, A. Gorad, A. Naik, A. Patil, and U. Ganguly, “Hardware-Friendly Synaptic Orders and Timescales in Liquid State Machines for Speech Classification,” in 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, Jul. 2021, pp. 1–8. doi: 10.1109/IJCNN52387.2021.9534021.
A. Kishore, V. Saraswat, and U. Ganguly, “Simplified Klinokinesis using Spiking Neural Networks for Resource-Constrained Navigation on the N euromorphic Processor Loihi,” in 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, Jul. 2021, pp. 1–8. doi: 10.1109/IJCNN52387.2021.9534471.
J. Choudhary, V. Saraswat, and U. Ganguly, “Algorithm for 3D-Chemotaxis Using Spiking Neural Network,” in Artificial Neural Networks and Machine Learning – ICANN 2021, Cham, 2021, pp. 207–219.
S. Shukla, R. Pathak, V. Saraswat, and U. Ganguly, “Adaptive Chemotaxis for Improved Contour Tracking Using Spiking Neural Networks,” in Artificial Neural Networks and Machine Learning – ICANN 2020, vol. 12397, I. Farkaš, P. Masulli, and S. Wermter, Eds. Cham: Springer International Publishing, 2020, pp. 681–692. doi: 10.1007/978-3-030-61616-8_55.
J. Sakhuja, S. Lashkare, V. Saraswat, and U. Ganguly, “Thermal Engineering of Volatile Switching in PrMnO3 RRAM: Non-Linearity in DC IV Characteristics and Transient Switching Speed,” in 2020 Device Research Conference (DRC), Jun. 2020, vol. 32, no. 8, pp. 1–2. doi: 10.1109/DRC50226.2020.9135171.
S. Landge, V. Saraswat, S. F. Singh, and U. Ganguly, “n-Oscillator Neural Network based Efficient Cost Function for n-city Traveling Salesman Problem,” in 2020 International Joint Conference on Neural Networks (IJCNN), Jul. 2020, pp. 1–8. doi: 10.1109/IJCNN48605.2020.9206856.
V. Saraswat, S. Lashkare, P. Kumbhare, and U. Ganguly, “Fundamental Limit on Network Size Scaling of Oscillatory Neural Networks due to PrMnO 3 based Oscillator Phase Noise,” in 2019 Device Research Conference (DRC), Jun. 2019, pp. 195–196. doi: 10.1109/DRC46940.2019.9046471.
A. Gorad, V. Saraswat, and U. Ganguly, “Predicting Performance using Approximate State Space Model for Liquid State Machines,” in 2019 International Joint Conference on Neural Networks (IJCNN), Jul. 2019, vol. 2019-July, pp. 1–8. doi: 10.1109/IJCNN.2019.8852038.
V. Saraswat and P. R. Nair, “Anomalous Scaling of Response Time of Chemical Sensors with Concentration of Unstable Gases,” Proceedings of IEEE Sensors, vol. 2018-Octob, pp. 1–4, 2018, doi: 10.1109/ICSENS.2018.8589789.
S. Lashkare, P. Kumbhare, V. Saraswat, S. Chatterjee, and U. Ganguly, “A Compact PrMnO<inf>3</inf> Based Oscillator as an Alternative to CMOS Ring Oscillator in a Smart Temperature Sensor,” in 2018 IEEE SENSORS, Oct. 2018, vol. 2018-Octob, no. c, pp. 1–4. doi: 10.1109/ICSENS.2018.8589573.
V. Saraswat and U. Ganguly, “Signs of Unconventional Physics in Long Channel Vertical InAs Nanowire MOSFETs,” Int. Work. Phys. Semicaonductor Devices, no. c, pp. 3–6, 2017.

Patents applied:

A. Biswas, V. Saraswat, U. Ganguly, “A method for Composite Spiking Neuron Networks (SNN) based Back-propagation for training Hardware” (Application No. 202221047747)
V. Saraswat, U. Ganguly “Stochastic invariance control in RRAM neurons” (Application No. 202121056949)
A. Singh, A. Kadam, V. Saraswat, M S Baghini, U Ganguly, “Recurrent neural network system based on Ultra-Low power neuron” (Application No. 202121055943)
V. Saraswat, S Deshmukh, S. Subramoney, U. Ganguly, “Temporary Memory for Inference and Learning in Neural Networks” (Application No.202221001342)
S. Lashkare, V Saraswat, P Kumbhare, U Ganguly, “Method for fabricating neuron oscillator including thermal insulating device” (Application No 201821019896)
U Ganguly, S Lashkare, V Saraswat, D Khilwani, V Moghe, P Kumbhare, M Shojaei Baghini, “PrxCa1-xMnO3 based Stochastic Neuron for Boltzmann Machine” (Application No 201921037296)

Page updated

Google Sites

Report abuse