Curious how you can convert already trained traditional ML models into tensor computations with up to 100x speedup?

Check out this blog post from Microsoft for details: https://azuredata.microsoft.com/articles/ebd95ec0-1eae-44a3-90f5-c11f5c916d15

Source code: https://github.com/microsoft/hummingbird

Learn AI/NLP and Machine Learning needed and deploy your own AI based Intelligent Chatbot.

Also learn how to earn cash after learning to build your own chatbot.

Kickstart your chatbot journey with our 6 Days Workshop starting from 12th June.

Participants will also get an AI Chatbot Cheetsheet and all the recorded sessions in free from theMAD.

The revolution of bots taking shape!

Are you part of this revolution?

Enroll now in just Rs 16 per day.

🔗 Link for enroll is here...

https://allevents.in/online/80002220391294


Other details on the above link 👆

Link : http://t.me/wethemadians

​​CREME – python library for online ML

All the tools in the library can be updated with a single observation at a time, and can therefore be used to learn from streaming data.

The model learns from one observation at a time, and can therefore be updated on the fly. This allows to learn from massive datasets that don't fit in main memory. Online machine learning also integrates nicely in cases where new data is constantly arriving. It shines in many use cases, such as time series forecasting, spam filtering, recommender systems, CTR prediction, and IoT applications. If you're bored with retraining models and want to instead build dynamic models, then online machine learning might be what you're looking for.

Here are some benefits of using creme (and online machine learning in general):
• incremental – models can update themselves in real-time
• adaptive – models can adapt to concept drift
• production-ready – working with data streams makes it simple to replicate production scenarios during model development
• efficient – models don't have to be retrained and require little compute power, which lowers their carbon footprint


api reference: https://creme-ml.github.io/content/api.html
github: https://github.com/creme-ml/creme

What Is Data Preparation in a Machine Learning Project
https://machinelearningmastery.com/what-is-data-preparation-in-machine-learning/

Creating Photo Mosaics Using Python
https://towardsdatascience.com/creating-photo-mosaics-using-python-49100e87efc

PULSE - Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models.

Research Paper: https://drive.google.com/file/d/1fV7FsmunjDuRrsn4KYf2Efwp0FNBtcR4/view

Code: https://github.com/adamian98/pulse

Other articles and sites:

https://techxplore.com/news/2020-06-artificial-intelligence-blurry-sharper.html

http://pulse.cs.duke.edu/

https://zentralwerkstatt.org/post_PULSE.html

https://towardsdatascience.com/explained-a-style-based-generator-architecture-for-gans-generating-and-tuning-realistic-6cb2be0f431

These fact checkers are LAME ASF

AnalyzeTheChat — Python-based WhatsApp chat analyzer
https://towardsdatascience.com/analyzethechat-python-based-whatsapp-chat-analyzer-cb53951c7ebb

SpineNet: A Novel Architecture for Object Detection Discovered with Neural Architecture Search
http://ai.googleblog.com/2020/06/spinenet-novel-architecture-for-object.html

🤯 What are tensors?

Learn from these amazing blogs:

👉🏼 A Gentle Introduction to Tensors for Machine Learning with NumPy by: Jason Brownlee. https://machinelearningmastery.com/introduction-to-tensors-for-machine-learning/

👉🏼 WTF is a Tensor?!? by: Matthew Mayo.
https://www.kdnuggets.com/2018/05/wtf-tensor.html

👉🏼 Quick ML Concepts: Tensors by: Chi Nok Enoch Kan.
https://towardsdatascience.com/quick-ml-concepts-tensors-eb1330d7760f

👉🏼 Our Instagram post covering this topic: https://www.instagram.com/p/CCSnIO9AVfd/?igshid=a2bgrgoip8zx

Happy learning! 🏁