Shreyas

@fastdotai International fellow | I am a tech geek interested in ML, Data Science, Analytics and Maths.

[Shreyas @Shreyas298]

1/I am glad to announce that our team (Aditya Malte, Sushant Rathi and I) are in the top 20 teams amongst the overall 2000 teams competing in the Microsoft AI Challenge.
Our task was to improve the Bing search engine. It was a great learning experience!#deeplearning #nlp #nlproc

[Shreyas @Shreyas298]

Wow !! Can't wait to get started on this. Love your top-down approach to teaching DL! I hope to create/do something meaningful at the end of this ! Thank you @jeremyphoward !

[Jeremy Howard @jeremyphoward]

Our new course, "From Deep Learning Foundations to Stable Diffusion", is finally done after 8 months of work!!!

With >30 hours of video content (all free, no ads!), you'll learn how to create and train a Stable Diffusion model starting from pure Python 🧵
https://t.co/bK0PSIzFww

[Ying Xiao @YingXiao]

Not sure to be proud or horrified that our Twitter recommendation work is now open sourced. Also, behold our unholy fusion of TensorFlow and Torch: https://t.co/MsfOCQ8i7R

[Sanyam Bhutani @bhutanisanyam1]

NLP with Transformers Study Group 🤗

Starting next week, I’m hosting a study group on the absolute gem book by @huggingface team 🙏

@_lewtun has kindly agreed to join the kickoff session. I can’t think of a better way to learn NLP:

https://t.co/rqSkC5HZni

[Uber Engineering @UberEng]

2022 Record Breaking News: Uber’s platform handled a new all time peak of 753K concurrent rides and deliveries 🎉🥳 What a way to close out the year!

[Emad @EMostaque]

Delighted to announce the public open source release of #StableDiffusion!

Please see our release post and retweet! https://t.co/dEsBX7cRHw

Proud of everyone involved in releasing this tech that is the first of a series of models to activate the creative potential of humanity

[Horace He @cHHillee]

Everybody wants their models to run faster. However, researchers often cargo cult performance without a solid understanding on the underlying principles.

To address that, I wrote a post called "Making Deep Learning Go Brrrr From First Principles". (1/3)

https://t.co/nhUct4R2SC

[AK @_akhaliq]

Block-NeRF: Scalable Large Scene Neural View Synthesis
abs: https://t.co/xDa1bmJaCJ
project page: https://t.co/IQTnknxTuK

[elvis @omarsar0]

Transformers from Scratch!

There are a lot of code implementations for Transformers out there and plenty of high-level explanations. However, none (from the ones I've seen) go as deep as this one. Awesome writeup by @_brohrer_. 👏🏻 Great for ML beginners.

https://t.co/ldBfhElCA4

[Chip Huyen @chipro]

I love teaching and I’ve always wanted to come back to Stanford to teach. After 2 years with the help of many people, it's happening!

I’ll be teaching Machine Learning Systems Design in Jan '21. It'll be online.

Syllabus is below. Feedback appreciated!

https://t.co/utXtcsaK82

[Zach Mueller @TheZachMueller]

With school over, I'll reveal one of my secrets. I'm making a new course!

Running with @fastdotai! Times and dates are TBD, but I'm shooting for this Fall to hold the course. This will be a continuation on Walk with fastai, building on what we learned there and applying it 1/

[Aman Arora @amaarora]

Here's a thread on why I write blogs and how that has completely changed my life.

https://t.co/3p3daaZV2y

1/

[Nando de Freitas @NandoDF]

Mike Jordan defending ML engineering! Good engineering gave us the GPU convnets, the transformers, torch, numpy, etc. The popular diminishing meme “it’s-just-engineering” is silly, and holds us back. I ❤️ creative, rigorous, robust, safe engineering. https://t.co/4GcTjf0d0F

[Aviral Bhatnagar @aviralbhat]

One of the biggest things I hear that constraints talented individuals is the “fear of failure”

But what it is it truly? A thread.

[Alex & Books 📚 @AlexAndBooks_]

7 Reading tips from @JamesClear

(thread) 🧵

[James Clear @JamesClear]

The 2-step process for exceptional results:

(1) Spend a little time each day thinking about the highest leverage activity available to you.

(2) Spend a little time each day working on it.

[Nisheeth Vishnoi @NisheethVishnoi]

1/6 Excited to announce that a draft of my book Algorithms for Convex Optimization (to be published by Cambridge) is available for download:

https://t.co/nY8Amdl580

Intended audience includes undergraduates, graduates and researches from TCS, optimization, and machine learning

[sanny @sannykimchi]

Everyone has heard about https://t.co/jug09Usgp7 or CS231n (for a good reason), but did you know you can access Stanford’s CS224w ML with Graphs or download the book Elements of Causal Inference for free? Thread on underappreciated ML resources 📚🎥 that deserve more love 👇 /1

[Navin Kabra @NGKabra]

"Dependency Injection is a 25-dollar term for a 5-cent concept. It means giving an object its instance variables. Really. That's it." —@jamesshore

https://t.co/4krLEcbeeW

[Shreyas @Shreyas298]

@A_K_Nain @abhi1thakur What you used to do in that 8hrs - 4-5hr block?

[Google DeepMind @GoogleDeepMind]

Interested in playing around with RL? We’re happy to announce the release of Acme, a light-weight framework for building and running novel RL algorithms.

We also include a range of pre-built, state-of-the-art agents to get you started. Enjoy! https://t.co/2wzpK3nCKp