- Papers on automated design of lightweight I/O cells for 2.5D system-in-package integration will be presented in IEEE S3S and IEEE EPEPS.
- Paper on a new AI algorithm that couples data-driven learning and model-based computation will be presented in the Conference on Robot Learning (CoRL).
- Paper on energy efficient and side-channel secure cryptographic hardware for IoT-edge devices is accepted for publications in IEEE Internet-of-Things Journal (IOT-J)
- Paper on Ferroelectric Field Effect Transistor (FeFET) based deep learning accelerator will be presented at IEEE/ACM ICCAD 2018.
- Paper on an accelerator for training deep learning network is accepted for presentation in ESWEEK 2018 and will be published in IEEE TCAD special issue.
- Two papers on smart sensors will be presented at IEEE S3S 2018. One paper will present an SoC for self-powered image sensor, and second paper will show the impact of 3D integration of mixed-signal neural network accelerator with digital pixel image sensors.
- Paper on an energy-quality scalable wireless image sensor node accepted for publications in IEEE Journal of Emerging and Selected Topics in Circuits and Systems (IEEE JETCAS).
- Paper on adversarial training for deep neural networks to increase robustness against adversarial attacks is accepted for International Conference on Learning Representation (ICLR), 2018:
- Paper on edge-host collaboration for intelligent surveillance is accepted in Design Automation Conference (DAC), 2018.
- Two papers accepted in International Conference on Acoustics, Speech and Signal Processing (ICASSP, 2018) on (i) anomaly detection using restricted Boltzman machines, and (ii) training algorithms for noise-robust DNN.
- Paper on an energy efficient and side-channel secure hardware architecture for lightweight cipher SIMON is accepted in IEEE International Symposium on Hardware Oriented Security and Trust (HOST), 2018.
- Paper on a System-In-Package based energy harvesting solution is accepted for IEEE Electronic Component and Technology Conference (ECTC), 2018
- GREEN Lab presented two invited papers at Design, Automation, and Test in Europe (DATE), 2018 on (i) side-channel security using on-chip power management circuits, and (ii) 3D stacked image sensor
- Paper on reducing power-side channel attack using integrated inductive voltage regulator accepted in IEEE Journal of Solid State Circuits (JSSC).
- Paper on designing recurrent neural network using resistive devices is accepted in IEEE Transactions on VLSI Systems (TVLSI).
- Paper on designing a 3D stacked image sensor with deep neural network computation is accepted in IEEE Sensors Journal (IEEE Sensors-J).
- Paper on designing an adaptive precision cellular nonlinear network is accepted in
- IEEE Transactions on VLSI Systems (TVLSI).
- Paper on a designing a DNN inference engine based on adaptive weight compression is accepted in IEEE Transactions on Computer Aided Design (TCAD).