1. A. Anwar and A. Raychowdhury, Multi-task federated reinforcement learning with adversaries, 2021. arXiv: 2103.06473 [cs.LG].

  2. A. Anwar and A. Raychowdhury, "Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes Using Transfer Learning," in IEEE Access, vol. 8, pp. 26549-26560, 2020.

  3. Yoon, Insik, Anwar, Malik Aqeel, Joshi, Rajiv, Rakshit, Titash and Arijit Raychowdhury. A Hierarchical Memory System with STT-MRAM and SRAM to Support Transfer and Real-time Reinforcement Learning in Autonomous Drones in IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS) (2019).

  4. Anwar, M.A., Siddique, A.B. and Tahir, M., 2016. Relative self-calibration of wireless acoustic sensor networks using dual positioning mobile beacon. IEEE Systems Journal, 12(1), pp.862-870


  1. Z. Wan, A. Anwar, Y.-S. Hsiao, T. Jia, V. Janapa Reddi, and A. Raychowdhury, “Analyzing and improving fault tolerance of learning-based navigation system,” ACM/EDAC/IEEE Design Automation Conference (DAC), 2021.

  2. A. Anwar and A. Raychowdhury, Masked face recognition for secure authentication, 2020. arXiv: 2008.11104

  3. S. Zeng, A. Anwar, T. Doan, J. Romberg, and A. Raychowdhury, A decentralized policy gradient approach to multi-task reinforcement learning, accepted in 37th Uncertainty in AI conference.

  4. A. Anwar, A. Raychowdhury, R. Hatcher and T. Rakshit, "XBAROPT - Enabling Ultra-Pipelined, Novel STT MRAM Based Processing-in-Memory DNN Accelerator," 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Genova, Italy, 2020, pp. 36-40, doi: 10.1109/AICAS48895.2020.9073792.

  5. Yoon, I., Anwar, A., Rakshit, T. and Raychowdhury, A., 2019, March. Transfer and Online Reinforcement Learning in STT-MRAM Based Embedded Systems for Autonomous Drones In 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE) (pp. 1489-1494). IEEE.

  6. Anwar, Malik Aqeel, and Arijit Raychowdhury. "NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images." 2018 25th International Conference on Mechatronics and Machine Vision in Practice (M2VIP). IEEE, 2018.

  7. Anwar MA, Hassan H, Maqbool H, Rehman A, Tahir M. Acoustic sensor network relative self-calibration using joint TDOA and DOA with unknown beacon positions. In2014 IEEE Wireless Communications and Networking Conference (WCNC) 2014 Apr 6 (pp. 3064-3069). IEEE.


  1. T. Rakshit, A. Anwar, and R. Hatcher, “Batch size pipelined PIM accelerator for vision inference on multiple images,” US20210124984A1, Apr 29, 2021, 2022. eprint:

  2. [P2] T. Rakshit, Anwar, and R. Hatcher, “Ultra-pipelined architecture for machine learning inference,” US2021012458A1, Apr 29, 2021, 2021. eprint: