Let’s start with the main principle. Rosetta@home is only predicting the molecular structure of synthetic drugs capable of Binding Covid-19 outer spike-in protein, which can be imagined as similar to the photographic technique in photography. Rosetta can statically predict the characteristics of a particular protein, but it cannot predict how that protein molecule will function under the evolution of time. Because there will be potential differences between molecules that generate…

NVIDIA CLARA DISCOVERY

Considering the existence of a large number of asymptomatic people in this epidemic, so this November holiday myself decided to DeepMind 2020 machine learning of the remaining six courses to finish, temporarily do not consider going on a trip.

Reference image and article address: [The next big thing: the use of graph neural networks to discover particles](https://news.fnal.gov/2020/09/the-next-big-thing- the-use-of-graph-neural-networks-to-discover-particles/)

Behind why deep learning is so powerful, we can think of the human brain’s neurons, which individually can’t do anything, but a bunch of neurons together are immensely powerful.

In the last week, I have been optimizing the Covid-Net I developed with my thesis and other research materials to diagnose the deep learning model of Covid19, and the accuracy I got from training on 20,000+ xRay datasets is less than 90%. When the model became more and more complex, the video memory was obviously not enough, so I sold the DJI Inspire 2 and used the money I earned to buy a TITAN RTX 24G, and then continued to optimize the model and increase training. of the batch_size.

The Mathematica + Python web framework is used to provide an external service platform, which, due to the fact that it is running on the machine, can be used as an external service. ARM Mathematica currently only supports 32-bit v6 v7, but a runtime library for armhf v6 v7 needs to be added to aarch64.

Tonight, I attended the Wolfram 2020 08-20 China Student Ambassador Presentation via Zoom.