zeonsky Goto Github PK

applied-ml

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

awd-lstm-lm

computer_vision_resnet_unet

I create this repository to review and breakdown SOTA deep learning applications on computer vision that benefit from the advent of ResNet and UNet.

computervision-recipes

Best Practices, code samples, and documentation for Computer Vision.

corona

Reverse engineering SARS-CoV-2

course-v3

The 3rd edition of course.fast.ai

cs229_ml

🍟 Stanford CS229: Machine Learning

deep-learning-for-tabular-data

My independent study of State-of-the-Art deep learning applications on tabular data

deep_autoencoder_financial_anomaly_detection

My work using deep autoencoder to detect financial anomalies in real world situation.

deep_learning_custom_loss

An on-going exercise to work upon a Kaggle dataset inspired by previous kernel contributors

deeplearning.ai-summary

This repository contains my personal notes and summaries on DeepLearning.ai specialization courses. I've enjoyed every little bit of the course hope you enjoy my notes too.

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

ensemble

Motivation: I create this repository for my independent study of top Kaggle winning solutions that uses ensemble method.

fast.ai_notes

:notebook: Notes for fast.ai courses: intro to ML, Practical DL and Cutting edge DL.

handson-ml2

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

imbalanced-data

I create this repository to start my study of top Kaggle winning solutions that deals with imbalanced data.

kaggle_healthcare

Independent study of top Kaggle winning solutions in the realm of healthcare

leetcode

Solutions to LeetCode Problems

lstm_stock_prediction_excercise

# An on-going excersise to work upon a Kaggle Kernel # https://www.kaggle.com/johanvandenheuvel/lstm-model-of-stockdata

lucid

A collection of infrastructure and tools for research in neural network interpretability.

machine-learning-learning-notes

周志华《机器学习》又称西瓜书是一本较为全面的书籍，书中详细介绍了机器学习领域不同类型的算法(例如：监督学习、无监督学习、半监督学习、强化学习、集成降维、特征选择等)，记录了本人在学习过程中的理解思路与扩展知识点，希望对新人阅读西瓜书有所帮助！

nested-logit-model-to-analyze-brand-competitiveness

My code using Nested Logit to optimize marketing resources for automobile industry.

pygcn

Graph Convolutional Networks in PyTorch

pygta5

Explorations of Using Python to play Grand Theft Auto 5.

python-code-mcmc-to-fit-the-shifted-beta-geometric-customer-lifetime-value-model

Two professors of marketing, Peter Fader and Bruce Hardie, have developed probability models for estimating customer lifetime value (LTV). In their papers and example spreadsheets, they estimate the models using maximum-likelihood estimation (MLE). In this post, I'm going to show how to use MCMC (via pymc) to estimate one of the models they've developed. Using MCMC makes it easy to quantify the uncertainty of the model parameters, and because LTV is a function of the model parameters, to pass that uncertainty through into the estimates of LTV itself. This post is primarily about implementing the model, and I'm only going to touch briefly on the strengths of the Fader/Hardie model over simpler, back-of-the-envelope formulas you'll find if you google 'calculate customer lifetime value.' But in the interest of motivating the implementation, the model is worth understanding because: by modeling the processes underlying aggregate metrics like 'churn rate' or 'repeated buying rate,' and by allowing for heterogeneity in a customer base, it provides more insight into customer behavior and in many cases, will provide less biased predictions about future behavior of customers.

pytorch-cifar10

CNN models on CIFAR10

pytorch-examples

Simple examples to introduce PyTorch

recommenders

Best Practices on Recommendation Systems

resnet-building-blocks-from-scratch

The ResNet (skip connections) has been the SOTA building block for recent deep learning advances. I create this repository to identify building blocks for ResNet and recreate them from scratch. Rebuilding this wheel is to prepare for future usage of ResNet without reinventing this wheel while maintaining a deep understanding of what's under the hood.