george-jiexiong Goto Github PK

chatpaper

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文总结+润色+审稿+审稿回复

cheatsheets-ai

Essential Cheat Sheets for deep learning and machine learning researchers https://medium.com/@kailashahirwar/essential-cheat-sheets-for-machine-learning-and-deep-learning-researchers-efb6a8ebd2e5

deep-learning-high-entropy-alloys

High Entropy Alloys (HEAs) are multi-chemical elements alloys with exceptional physical properties. HEAs have sparked the interest in engineering applications such as energy storage, catalysis and bio/plasmonic imaging. The understanding of the structural of composition of HEAs is paramount for the appropriate tuning of their properties. Scanning Transmission Electron Microscopy (STEM) is typically used to acquire images of various materials at the atomic scale resolution. including HEAs. In this repository it is demonstrated how computer vision analysis based on Deep Learning (DL) could be used to extract structural information from STEM images of HEAs. In particular a Fully Convolutional Neural Network (FCN) is trained to recognize the number of atoms of different chemical species in the atomic columns of HEA (i.e., column heights CHs) through semantic segmentation of simulated and experimental STEM images. As a benchmark case, equiatomic PtNiPdCoFe HEAs are considered. This project represent a first attempt for the identification of chemical species in 3D materials. Thus, in addition to the estimation of the structural properties of HEAs, this work establish an advancement of DL applied to microscopy image which could be useful for a broad area of nano-science applications.

image

materials-dataset

mlmd-data

multi-armed-bandit

A basic implementation of techniques to solve the Multi-Armed bandit (MAB) problem from the context of a marketing strategy. A couple of techniques namely the Epsilon-Greedy Approach, Upper Confidence Bound (UCB), Gradient Ascent and Thompson Sampling have been used to analyze choosing the best website in terms of receiving a click.

nanogpt

The simplest, fastest repository for training/finetuning medium-sized GPTs.

onlineresume

pymatgen

Python Materials Genomics (pymatgen) is a robust materials analysis code that defines core object representations for structures and molecules with support for many electronic structure codes. It is currently the core analysis code powering the Materials Project.

research-group

tradaboost

Boosting for transfer learning with single / multiple source(s) Regression / Classification

transferlearning

instance based Transfer learning, TrAdaboost, mutisource-trAdaBoost regresion

tutorials

Tutorials on deep learning, Python, and dissipative particle dynamics

two-stage-tradaboost.r2