• Prof. Sourajeet Roy and Prof. Avirup Dasgupta will be showcasing the research output of CMAS and DiRac Lab in their tutorial entitled 'Metalearning Advances in Machine Learning for Modeling of Emerging FET Devices and Interconnects below 10nm Technology Nodes' at the 32nd IEEEE EPEPS conference.

​

• Congratulations to Asha and Surila Guglani for getting our paper entitled 'Prior knowledge accelerated transfer learning (PKI-TL) for machine learning assisted uncertainty quantification of MLGNR interconnect networks' accepted for oral presentation in 32nd IEEEE EPEPS conference. This paper is part of the Special Session on Machine Learning.

​

• Prof. Avirup Dasgupta and Prof. Sourajeet Roy will be jointly organizing the 2nd Sort course on Machine Learning for Electron Devices (MLED'23)from 3rd - 6th October 2023. This will be an in-person short course organized by iHUB DivyaSampark and the ECE department of IIT Roorkee (website).

​

• Congratulation to Aasim Ashai for getting our paper entitled 'Deep Learning Based Fast BSIM-CMG Parameter Extraction for General Input Dataset' accepted for publication in IEEE Transactions on Electron Devices!!! This is a joint work with the DiRaC Laboratory.

​

• Congratulation to Dimple and Surila Guglani for getting our paper entitled 'Modified Knowledge-Based Neural Networks Using Control Variates for the Fast Uncertainty Quantification of On-Chip MWCNT Interconnects' accepted for publication in IEEE Transactions on Electromagnetic Compatability.

​

• Congratulations to Surila Guglani and Dimple for getting our paper entitled 'A Bilevel Multi-fidelity Polynomial Chaos Approach for the Uncertainty Quantification of MWCNT Interconnect Networks with Variable Imperfect Contact Resistances' accepted for publication in the IEEE Access

​

• Prof. Roy will be presenting an invited lecture entitled 'Machine Learning Techniques as Alternative to Physics-Based Parametric Device Model Development' at the prestigious 6th International Conference on Emerging Electronics in Bengaluru, India

​

• We are happy to announce that our proposal titled Machine Learning Augmented SPICE Models for Efficient Circuit Design has been accepted for funding by the Semiconductor Research Corporation India Call 2022. The funding is for 3 years and will help realize our shared vision of leveraging the generalization capacity of machine learning metamodels to improve the computational speed and accuracy of current industrial standard compact models for nanoscale FETs.
  ​

• Congratulations to Suyash Kushwaha and our partners at Politecnico de Torino for getting our paper entitled 'Comparative Analysis of Prior Knowledge-Based Machine Learning Metamodels for Modeling Hybrid Copper-Graphene On-Chip Interconnects' accepted for publication in the IEEE Transactions on Electromagnetic Compatibility. 

​

• Congratulations to Aakash Yadav and Prof. Biplab Sarkar for getting our paper entitled 'An Accurate Approach to Develop Small Signal Circuit Models for AlGaN/GaN HEMTs using Rational Functions and Dependent Current Sources' accepted for publication in the IEEE Journal of Electron Devices. 

​

• Congratulations to Surila and Km Dimple for getting our paper entitled 'A Transfer Learning Approach to Expedite Training of Artificial Neural Networks for Variability-Aware Signal Integrity Analysis of MWCNT Interconnects' accepted for oral presentation in EPEPS 2022. This is our latest work with the DiRac Lab.

​

• Congratulations to Adeeba for getting our paper entitled 'An Artificial Neural Network Surrogate Model for Repeater Optimization in the Presence of Parametric Uncertainty for Hybrid Copper-Graphene Interconnect Networks' accepted for oral presentation in 2022 IEEE MTT-S NEMO.

​

• Congratulations to Dimple, Surila Guglani, and Rahul Kumar for getting our paper entitled 'Exploring the Impact of Parametric Variability on Eye Diagram of On-Chip Multi-walled Carbon Nanotube Interconnects using Fast Machine Learning Techniques' accepted for oral presentation in 2022 IEEE 72nd Electronic Components and Technology Conference.

​

• We are excited to announce that our recent paper titled 'A polymorphic polynomial chaos formulation for mixed epistemic-aleatory uncertainty quantification of RF/Microwave circuits' authored by my Ph. D. student Mohd. Yusuf has been accepted for publication in the Special Issue of the IEEE Transaction on Microwave Theory and Techniques.

​

• Our recent paper titled 'Modified Small Signal Circuit of AlGaN/GaN MOS-HEMTs using Rational Functions' has been accepted for publication in the IEEE Transaction on Electron Devices. This work is an outcome of the collaboration of CMAS research group with the Wide Bandgap research group in IIT Roorkee and the Department of Electrical Engineering and Computer Science, Nagoya University, Japan. 

​

• The CMAS research group is partnering with the DiRac Laboratory to look into machine learning based solutions to modeling solutions for emerging nanoscale semiconductor devices. To that end, we are actively seeking new Ph. D. students (details given here).

​

• We are excited to announce that our paper titled 'Fast Extraction of Per-Unit-Length Parameters of Hybrid Copper-Graphene Interconnects via Generalized Knowledge Based Machine Learning' authored by Ph. D. student Suyash Kushwaha has been accepted for oral presentation in EPEPS 2021. This is the first publication coming from the tripartite collaboration between IIT Roorkee, IIT Ropar, and Politecnico di Torino.

​

• Our project titled 'Fast Machine Learning-Based Parametric SPICE Macromodel Extraction for FinFET Device-to-System Level Optimization' has been selected for funding by our industrial partner Qualcomm as part of the 2021 Qualcomm Innovation Fellowship India. Congratulations to Surila Guglani for spearheading the proposal with our collaborator Sudeb Dasgupta and his student Jyoti Patel. This proposal will enable the deployment of machine learning-assisted EDA tools for the modeling of nanoscale FinFET devices at millimeter-wave frequencies for 5G applications. https://www.qualcomm.com/research/university-relations/innovation-fellowship/2021-india

​​

• Our recent paper titled 'Generalized Frequency-Dependent Small-Signal Model for High Frequency ' Analysis of AlGaN/GaN MOS-HEMTs' has been accepted for publication in the IEEE Journal of Electron Devices Society. This work is an outcome of the collaboration of CMAS research group with the Wide Bandgap research group in IIT Roorkee and the Department of Electrical Engineering and Computer Science, Nagoya University, Japan. ​​​​​​​​​​