2021

• Souvik Kundu, M. Pedram, P. A. Beerel:
  HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise
  International Conference on Computer Vision (acceptance rate: 25.9%, h5 index: 184), 2021

• Souvik Kundu, Q. Sun, Y. Fu, M. Pedram, P. A. Beerel:
  Skeptical Student: Diminishing the Effect of Nasty Teacher in Knowledge Distillation
  Computer Vision and Pattern Recognition (Workshop on Responsible Computer Vision), 2021

• Gourav Datta, Souvik Kundu, P. A. Beerel:
  Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding
  International Joint Conference on Neural Networks (IJCNN), 2021

• S. Dey, S. Babakniya, S. Kanala, M. Paolieri, L. Golubchik, P.A. Beerel, K.M. Chugg:
  Deep-n-Cheap: An Automated Efficient and Extensible Search Framework for Cost-Effective Deep Learning
  SN Computer Science, 2021.

• Souvik Kundu, Sairam Sundaresan:
  AttentionLite: Towards Efficient Self-Attention Models for Vision
  International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021

• Daniel Beauchamp, Keith M. Chugg:
  Linearization for High-Speed Current-Steering DACs Using Neural Networks
  IEEE Latin America Symposium on Circuits and System (LASCAS), 2021.

• Souvik Kundu, Gourav Datta, Massoud Pedram, Peter A. Beerel:
  Spike-Thrift: Towards Energy-Efficient Deep Spiking Neural Networks by Limiting Spiking Activity via Attention-Guide Compression,
  Winter Conference on Applications of Computer Vision (WACV), 2021

• Souvik Kundu, Mahdi Nazemi, Peter A. Beerel, Massoud Pedram:
  DNR: A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs
  Asia and South Pacific Design Automation Conference (ASP-DAC), 2021

2020

• C.-L. Chen, Leana Golubchik, Marco Paolieri:
  Backdoor Attacks on Federated Meta-Learning
  NeurIPS-SpicyFL, 2020.

• Sourya Dey, Saikrishna Kanala, Keith M. Chugg, Peter A. Beerel:
  Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep Learning
  Asian Conference on Machine Learning (ACML), 2020.

• Daniel Beauchamp, Keith M. Chugg:
  Machine Learning Based Image Calibration for a Twofold Time-Interleaved High Speed DAC
  IEEE International Midwest Symposium on Circuits and Systems (MSCAS), 2019

• Souvik Kundu, Mahdi Nazemi, Massoud Pedram, Keith M. Chugg, Peter Beerel:
  Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks
  IEEE Transactions on Computers, 2020.

• Arnab Sanyal, Peter Beerel, Keith M. Chugg:
  Neural Network Training with Approximate Logarithmic Computations
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020

2019

• Zhuojin Li, Wumo Yan, Marco Paolieri, Leana Golubchik:
  Throughput Prediction of Asynchronous SGD in TensorFlow
  CoRR abs/1911.04650 (2019) | Accepted for publication at ICPE 2020

• Amir Erfan Eshratifar, Amirhossein Esmaili, Massoud Pedram:
  BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services
  IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)

• Amir Erfan Eshratifar, Mohammad Saeed Abrishami, Massoud Pedram:
  JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services
  IEEE Transactions on Mobile Computing

• Souvik Kundu, Saurav Prakash, Haleh Akrami, Peter Beerel, Keith M. Chugg:
  PSConv: A Pre-Defined Sparse Kernel Based Convolution for Deep CNNs
  Allerton Conference on Communication, Control, and Computing (Allerton), 2019

• Arash Fayyazi*, Souvik Kundu*, Shahin Nazarian, Peter A. Beerel, Massoud Pedram:
  CSrram: Area-Efficient Low-Power Ex-Situ Training Framework for Memristive Neuromorphic Circuits Based on Clustered Sparsity
  To appear in IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 2019
  * = Authors have equal contribution

• Sourya Dey, Kuan-Wen Huang, Peter A. Beerel, Keith M. Chugg:
  Pre-Defined Sparse Neural Networks with Hardware Acceleration
  IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS)

• Mahdi Nazemi, Ghasem Pasandi, Massoud Pedram:
  Energy-Efficient, Low-Latency Realization of Neural Networks Through Boolean Logic Minimization
  Proceedings of the 24th Asia and South Pacific Design Automation Conference (ASP-DAC)

2018

• Sung-Han Lin, Marco Paolieri, Cheng-Fu Chou, Leana Golubchik:
  A model-based approach to streamlining distributed training for asynchronous SGD
  MASCOTS 2018, Milwaukee, WI, USA
• Sourya Dey, Diandian Chen, Zongyang Li, Souvik Kundu, Kuan-Wen Huang, Keith M. Chugg, Peter A. Beerel:
  A Highly Parallel FPGA Implementation of Sparse Neural Network Training
  Reconfig 2018, Cancun, Mexico
  See arXiv for expanded pre-print version
• Sourya Dey, Keith M. Chugg, Peter A. Beerel:
  Morse Code Datasets for Machine Learning
  Awarded Best Paper at ICCCNT 2018, Bengaluru, India
  Code available on Github
• Sourya Dey, Kuan-Wen Huang, Peter A. Beerel, Keith M. Chugg:
  Characterizing Sparse Connectivity Patterns in Neural Networks
  ITA Workshop 2018, San Diego, CA, USA

2017

• Sourya Dey, Peter A. Beerel, Keith M. Chugg:
  Interleaver design for deep neural networks
  ACSSC 2017, Asilomar, CA, USA
• Sourya Dey, Yinan Shao, Keith M. Chugg, Peter A. Beerel:
  Accelerating Training of Deep Neural Networks via Sparse Edge Processing
  ICANN 2017, Alghero, Italy