## Kaushik

- 2019 [Neural network accelerator design with resistive crossbars: Opportunities and challenges](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5166/jain2019.pdf)

- open source - [PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5161/ankit2019.pdf)  ankit 2019

- [Computing in Memory With Spin-Transfer Torque Magnetic RAM](https://arxiv.org/pdf/1703.02118.pdf)

- 2021 [Roadmap of spin-orbit torques](https://arxiv.org/abs/2104.11459) Qiming Shao

- 2020 [On the Intrinsic Robustness of NVM Crossbars Against Adversarial Attacks](https://arxiv.org/abs/2008.12016) Deboleena Roy

## DL recommended

- ML

2019 [Back to Simplicity: How to Train Accurate BNNs from Scratch?](https://arxiv.org/abs/1906.08637) Joseph Bethge

2019 [Invariant Risk Minimization](https://arxiv.org/abs/1907.02893) Martin Arjovsky