👩🏻‍💻 Why should one study Linear Algebra for ML?

👉🏼 Clearly, to develop a better intuition for machine learning and deep learning algorithms and not treat them as black boxes. This would allow you to choose proper hyper-parameters and develop a better model. You would also be able to code algorithms from scratch and make your own variations to them as well.

👉🏼 Learn Linear Algebra for Machine Learning with:

Khan Academy: https://www.khanacademy.org/math/linear-algebra

Udacity: https://www.udacity.com/course/linear-algebra-refresher-course--ud953

Coursera: https://www.coursera.org/learn/linear-algebra-machine-learning

Here are some amazing freely available ebooks on the same topic:

Mathematics for Machine Learning: https://mml-book.github.io/book/mml-book.pdf

An Introduction to Statistical Learning: https://faculty.marshall.usc.edu/gareth-james/ISL/

Happy machine learning! 🎉

🤓 Free blog-course on machine learning!

https://www.c-sharpcorner.com/learn/learn-machine-learning-with-python

Hope y'all find it useful! 🙌🏼

🤯 A new model can detect deepfake images by looking at subtle visual artifacts like textures in hair, backgrounds and faces.

It creates heatmaps that pinpoint manipulated areas and exaggerate their effects.

Paper/Code: https://chail.github.io/patch-forensics/

🙌🏼 AutoML provides tools to automatically discover good machine learning model pipelines for a dataset with very little user intervention.

👉🏼 It is ideal for domain experts new to machine learning or machine learning practitioners looking to get good results quickly for a predictive modeling task. Open-source libraries are available for using AutoML methods with popular machine learning libraries in Python, such as the scikit-learn machine learning library.

👉🏼 In this tutorial, you will discover how to use top open-source AutoML libraries for scikit-learn in Python. Link: https://machinelearningmastery.com/automl-libraries-for-python/

🥳 20+ awesome data-science project ideas for beginners!

https://www.linkedin.com/posts/priyanka-kasture_mli-data-science-projects-activity-6724679474480242688-7pP4

A very interesting story of how the iPod was created. Must read! ❤️👇🏼

https://www.linkedin.com/posts/priyanka-kasture_apple-stevejobs-steve-activity-6731914678764679168-80xs

Awesome key-board shortcuts for data scientists! 🤓👇🏼

https://www.linkedin.com/posts/mlindia_keyboard-shortcuts-for-data-scientist-activity-6716221331727290368-tRjf

🤓 Ready-to-use OCR with 70+ languages supported including Chinese, Japanese, Korean and Thai - EasyOCR (https://github.com/JaidedAI/EasyOCR)

Google's star ethics researcher - Timnit Gebru, highlighted the risks of large language models, which are key to Google's business.

And then, Google forced her out of the company.

Read the details about the ground-breaking paper, here: https://www.technologyreview.com/2020/12/04/1013294/google-ai-ethics-research-paper-forced-out-timnit-gebru/

🚙 Baidu, on Thursday announced the release of ApolloScape, billed as the world’s largest open-source dataset for autonomous driving technology!

The data volume of ApolloScape is 10 times greater than any other open-source autonomous driving dataset, including Kitti and CityScapes. This data can be utilized for perception, simulation scenes, road networks etc., as well as enabling autonomous driving vehicles to be trained in more complex environments, weather and traffic conditions.

Find the details here: https://medium.com/@Synced/baidu-apollo-releases-massive-self-driving-dataset-teams-up-with-berkeley-deepdrive-5e785ab4053b

Find the dataset here: http://apolloscape.auto/

Change the background of any video with 5 lines of code! 🤓 How? With PixelLib. Learn here: https://www.kdnuggets.com/2020/12/change-background-video-5-lines-code.html

You can also blur, color, grayscale and create a virtual background for a video with PixelLib!

PapersWithCode has introduced 'Datasets', find 3046 of them on the link: https://www.paperswithcode.com/datasets 🚀

A genealogy-tracking service called MyHeritage has launched an AI-powered tool it calls 'Deep Nostalgia' which animates old photos of users' family members, whether deceased or otherwise! 😳

Try it out: https://www.myheritage.com/deep-nostalgia

Neural Networks: A Cheatsheet, by becominghuman.ai 🤓