The last two days the company planned a hackathon competition, they simply signed up to participate, thinking that they are currently researching the topic of deep learning, on the Google search blockchain deep learning, and finally found this paper Energy-recycling Blockchain with Proof-of-Deep-Learning, and then developed a PoDL chain for storing deep models along the lines of the paper, which is presented below, followed by Mathematica and Python implementations. Program Code.

The following topics are of interest to me, and I am currently starting my own business in Wolfram and Python, with Wolfram being the main language for prototyping and exploring initial ideas. After watching the following presentations, I will focus on biomedical and retinal image analysis as a deep learning research topic.

Today, in the course of work, I need to parse a JSON file to get a keyword, and I’m going to use Mathematica to practice.

The animation program code is as follows:

I have written an article about how to build a distributed training cluster on Raspberry Pie 4 using the distributed training system that comes with TF2.0. However, there is a drawback: we need to start the training program at each node, and the distributed training will only work after all the nodes are started. MPI is mainly used in the field of supercomputing. Building MPI cluster on Raspberry, firstly, it can be used to learn distributed computing on supercomputing, and secondly, it can…

Video address of the online seminar

Tensorflow Converter can convert models to FlatBuffers format. FlatBuffers is a cross-platform serialization tool where structured data is stored in binary form and can be used in the following ways The performance on the microcontroller is memory saving.