Artificial Intelligence using Emerging Eevices and Architectures


Dr. Debanjan Bhowmik


Assistant Professor
Department of Electrical Engineering
Indian Institute of Technology Delhi


Tuesday, 11 February 2020, 14:00 to 15:00


  • A-201 (STCS Seminar Room)


Abstract: Artificial Intelligence (AI)/ Machine Learning (ML)/ Neural Network (NN) algorithms are being widely used currently for various applications that include self driving cars, virtual assistants on smartphones and other devices, etc. However, the memory-computing separation in existing computer hardware makes implementation of these algorithms on the hardware inefficient in terms of power and speed. As a result, new devices and architectures are being proposed to run these algorithms more efficiently.

In this context, I will discussed the latest work carried out in our research group on the implementation of AI/ML/NN algorithms in a crossbar based in-memory computing architecture, as well as a quantum architecture. For the former, we have used both spin based devices (spin orbit torque driven domain wall devices) [1,2,3] and charge based devices (a single conventional silicon transistor synapse) [4]. We have used both non-spiking NN algorithms, used abundantly in the ML community, [2,4] as well as spiking NN algorithms, inspired from the working of the brain [3]. For the latter, we have proposed a novel quantum algorithm, implemented it on the "qiskit" simulation framework and shown very high classification accuracy on different popular ML datasets [5].


1. Debanjan Bhowmik et al. "Deterministic domain wall motion orthogonal to current flow due to spin orbit torque". Scientific Reports , Vol. 5, 11823 (2015)
2. Debanjan Bhowmik et al. "On-chip learning for domain wall synapse based Fully Connected Neural Network". Journal of Magnetism and Magnetic Materials Vol. 489, 165434 (2019)
3. Upasana Sahu, Aadit Pandey, Kushaagra Goyal and Debanjan Bhowmik. "Spike time dependent plasticity (STDP) enabled learning in spiking neural networks using domain wall based synapses and neurons". AIP Advances Vol. 9, 12 (2019)
4. Nilabjo Dey, Janak Sharda, Utkarsh Saxena, Divya Kaushik, Utkarsh Singh, Debanjan Bhowmik. "On-Chip Learning in a Conventional Silicon MOSFET Based Analog Hardware Neural Network". IEEE Biomedical Circuits and Systems Conference (BioCAS), Nara, Japan (2019)
5. S. Adhikary, S. Dangwal and D. Bhowmik, Supervised learning with a quantum classifier using multi-level systems, Quantum Information Processing 19, 89 (2020).

Bio: Dr. Debanjan Bhowmik is currently an Assistant Professor in the Department of Electrical Engineering, Indian Institute of Technology Delhi. He obtained his BTech degree in Electrical Engineering from Indian Institute of Technology Kharagpur in 2010. He obtained his PhD degree from University of California Berkeley in 2015, working in the field of nano magnetism and spintronics. Currently at IIT Delhi he works on Artificial Intelligence using emerging devices like spintronic devices and emerging architectures like in-memory computing architecture and quantum architecture.