|
 |
On the cover: Medicine is the practice of the diagnosis, treatment, and prevention of disease. With the advances in medical science, human beings are getting both longer life spans and higher quality of life. From herbs to molecular signatures, humankind is experiencing a transition from traditional medicine to personalized medicine: the right treatment to the right patient at the right time. However, it is not so easy to achieve this goal because the etiology of most diseases and disorders is still unclear. From description to association, numerous researchers are working together to decipher the mechanisms behind disease. To address such challenges, more and more global collaborations are badly needed to include experts from all disciplines: not just doctors, scientists and administration staff, but also engineers, technicians and marketing managers. Not limited to a fish-eye view, we humans should widen our vision and get more deep insights beyond the human community. That is the right way to assure sustainable healthcare for humanity. |
|
|
Add comment (English only) |
|
|
|
|
|
Position: Home > issue > May 10, 2022 Volume 3, Issue 3 |
|
|
|
Accelerating deep learning with high energy efficiency: From microchip to physical systems |
Category: Commentary Download: PDF Figure Endnote |
Author: Huanhao Li, Zhipeng Yu, Qi Zhao, Tianting Zhong, Puxiang Lai |
|
|

Diagram of deep learning realizations
In the era of digits and internet, massive data have been continuously generated from a variety of sources, including video, photo, audio, text, internet of things, etc. It is intuitive that more accurate patterns can be obtained by feeding more data for effective analysis; despite the data redundancy, a clearer picture can be delineated for better decision-making. However, traditional methods, even in machine learning, do not benefit from the expanding amount of data, whose performance nearly saturates when the data collection is large enough.

|
|
|
|