A base solution that helps to generate insights from their data. The solution provides a framework for an end-to-end machine learning process including ad-hoc data exploration, data processing and feature engineering, and modeling training and evaluation. This baseline will provide the foundation for industry specific data to be applied and models created to release industry specific ML solutions.

Kaggle 入门教程

Code exercises and demos complementing lecture materials.

MICCAI18 DeepEM: Deep 3D ConvNets with EM for Weakly Supervised Pulmonary Nodule Detection

RETIRED - instead use https://github.com/robmarkcole/HASS-Deepstack-object

GSOC 2017 - Apache Organization - # Implementation of Factorization Machines on Spark using parallel stochastic gradient descent (python and scala)

Jupyter widget for quick visualization of Pandas dataframes using Vega and Altair

Skin cancer classification using Inceptionv3

An Analysis of the Distribution Law of Word Frequency and Stroke Number in Chinese

CoCalc: Collaborative Calculation in the Cloud

Here, we will upload our deep/machine learning models and 'workflows' (such as AtomNet, DefectNet, SymmetryNet, etc) that aid in automated analysis of atomically resolved images

📊 Visualization of GTD with py Plotly lib, including amazing graphs and animation 📼