Data Science Digest

2021-04-20 13:09:40 ​​OpenCV Face Detection with Haar Cascades

Face detection is one of the most popular Computer Vision use cases (at least, as perceived by the general public). Learning how to use OpenCV and Haar Cascades can be critical if you want to go deep with the field — and this detailed tutorial provides a fresh and easy start for new learners. Just follow the instructions step by step and see the results in action.

https://bit.ly/3v5C3KB

@DataScienceDigest Open / Comment

2021-04-19 12:50:15 ​​How Graph Neural Networks (GNN) Work: Introduction to Graph Convolutions from Scratch

The title of this one is quite self-explanatory — The author explores graph neural networks and graph convolutions to explain how they work and how you can apply them in theory and practice in your projects. All points are illustrated with code for convenience.

https://bit.ly/3mY2cYS

@DataScienceDigest Open / Comment

2021-04-18 11:00:07 ​​Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning

In this paper, Fatemeh Haghighi and the team of authors introduce a new concept called «transferable visual words» (TransVW), which is designed to help achieve annotation efficiency for deep learning in medical image analysis. Learn about the team’s extensive experiments and the advantages that TransVW has demonstrated. The research is available as code, pre-trained models, and curated visual words.

Paper — https://bit.ly/3gjtZlj
Code — https://bit.ly/32ms9rP

Subscribe to our weekly newsletter — https://bit.ly/3ahhZNd Open / Comment

2021-04-17 11:06:33 ​​Paper Review: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Microsoft Research Asia has presented a brand new vision Transformer called Swin Transformer that can serve as a backbone like usual CNNs in computer vision and Transformers in natural language processing. The author provides a detailed review of the paper, exploring all the do’s and don’ts of the new approach and the possibilities it offers for developing a unified architecture for CV and NLP tasks.

https://bit.ly/32nLZTu

Subscribe to our weekly newsletter — https://bit.ly/3tvunB8 Open / Comment

2021-04-16 11:40:01 ​​Weekly Awesome Tricks And Best Practices From Kaggle

Kaggle is a go-to destination for data scientists and ML engineers for a reason. It features tons of valuable resources and hosts competitions covering pretty much each and every existing/potential topic in the industry. But how do you take the most out of the platform? Check out this article with tips, tricks, and best practices on using Kaggle during a typical data science workflow.

https://bit.ly/3agM0No

Subscribe to our weekly newsletter — https://bit.ly/3wTjKdg Open / Comment

2021-04-15 13:09:06 Hi folks, DataScience Digest is back on track. In fact, our readers got the first email newsletter just yesterday. Interested in weekly updates about AI, ML too?

Kindly subscribe here: https://bit.ly/3acYHc4.

The newsletter is sent out every Wednesday. Stay tuned! Open / Comment

2021-04-15 10:15:05 ​​A Machine Learning Model Monitoring Checklist: 7 Things to Track

Once the model is deployed in production, you need to ensure it performs and that you have accounted for data/mode drift and other changes affecting accuracy and precision. Here comes model monitoring! This article will look into the specifics of model monitoring and explore open-source tools that you can start using today. It also features a short, 7-step checklist to help you make machine learning work in the real world.

https://bit.ly/3slqg96

Subscribe to our weekly digest — https://bit.ly/3smtHwp Open / Comment

2021-04-14 09:30:06 ​​How to Deploy Machine Learning / Deep Learning Models to the Web

Machine and deep learning models should not exist in a vacuum (theoretical environments). They need to be deployed in production and used by businesses/customers. In this article, the author provides a step-by-step guide on deploying models to the web and accessing them as a REST API using Heroku and GitHub. You will also learn how to access that API using the Python requests module and CURL.

https://bit.ly/2OKpXqI

Join @DataScienceDigest Open / Comment

2021-04-13 21:35:27 ​​Transfer Learning and Data Augmentation Applied to the Simpsons Image Dataset

In this article, the author uses the Simpsons characters dataset to experiment with data augmentation for transfer learning. Through image filtering to splitting, testing, and validating datasets, a series of experiments is conducted to address the problem of small datasets and overfitting. Check out this step-by-step guide to learn about the results and the final metrics that the experiments yielded.

https://bit.ly/3wQuqJN

Join @DataScienceDigest Open / Comment

2021-04-09 09:00:10 ​​The Applied Machine Learning Course at Cornell Tech

Starting from the very basics, the course covers the most important ML algorithms and how to apply them in practice. The slides are Jupyter notebooks with programmatically generated figures so that readers can tweak parameters and regenerate the figures themselves. The course explores topics such as how to prioritize model improvements, diagnose overfitting, perform error analysis, visualize loss curves, etc.

Course Videos: https://bit.ly/3dLKZha
Course Materials: https://bit.ly/2Rmlj3e

Join @DataScienceDigest Open / Comment