## 2020 - Review [An Updated Survey of Efficient Hardware Architectures for Accelerating Deep Convolutional Neural Networks](https://res.mdpi.com/d_attachment/futureinternet/futureinternet-12-00113/article_deploy/futureinternet-12-00113-v2.pdf) Maurizio Capra


![yy](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5295/comparison%2Blast%2B3%2Byears.PNG 'yy')


## 2020 [A Survey of Accelerator Architectures for Deep Neural Networks](https://www.sciencedirect.com/science/article/pii/S2095809919306356) Yiran Chen

> Although the explosion of big data applications is driving the development of ML, it also imposes severe challenges of data processing speed and scalability on conventional computer systems.


## 2013 [Finding a roadmap to achieve large neuromorphic hardware systems](https://www.frontiersin.org/articles/10.3389/fnins.2013.00118/full) Jennifer Hasler and Bo Marr

2019 [Analog Architecture Complexity Theory Empowering Ultra-Low Power Configurable Analog and Mixed Mode SoC Systems](https://www.mdpi.com/2079-9268/9/1/4/htm) by Jennifer Hasler

## 2020 [Mixed-precision architecture based on computational memory for training deep neural networks](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5194/nandakumar2018.pdf) S. R. Nandakumar

> We propose **a mixed-precision architecture that combines a computational memory unit** storing the synaptic weights with
> a digital processing unit and an additional memory unit that stores the accumulated weight updates in high precision. The
> new architecture delivers classification accuracies comparable to those of floating-point implementations without being constrained by challenges associated with the non-ideal weight update characteristics of emerging resistive memories.

youtube [Working at the Intersection of Machine Learning, Signal Processing, Sensors, and Circuits]() Dina Katabi

## new devices

2020 [NeuroMem: Analog Graphene-Based Resistive Memory for Artificial Neural Networks](https://www.nature.com/articles/s41598-020-66413-y) Heba Abunahla

- 2018 Li-ion [ECRAM as Scalable Synaptic Cell for High-Speed, Low-Power Neuromorphic Computing](https://ieeexplore.ieee.org/document/8614551) Jianshi Tang