Twitter | Search | |
This is the legacy version of twitter.com. We will be shutting it down on 15 December 2020. Please switch to a supported browser or device. You can see a list of supported browsers in our Help Center.
Sohil Newa
Introvert || PhD Student at || Machine Learning || Software Engineering
872
Tweets
132
Following
174
Followers
Tweets
Sohil Newa retweeted
Kritika Prakash @ NeurIPS 2020 Nov 17
How to build a strong technical background in Deep Learning? Build your own Neural Network Library. Use 's resources along with insights from 's courses (Intro to ML + DL Specialization) Personal recommendation: **Grokking Deep Learning** by 💯
Reply Retweet Like
Sohil Newa retweeted
Andrej Karpathy Nov 7
How to become expert at thing: 1 iteratively take on concrete projects and accomplish them depth wise, learning “on demand” (ie don’t learn bottom up breadth wise) 2 teach/summarize everything you learn in your own words 3 only compare yourself to younger you, never to others
Reply Retweet Like
Sohil Newa Nov 7
--. --- --- -.. / -.. .- -.--
Reply Retweet Like
Sohil Newa retweeted
Michael Bronstein Sep 15
A new post coauthored with Kirill Veselkov and Gabriella Sbordone on the use of for discovering -beating molecules in and the concept of based on our Scientific Reports paper
Reply Retweet Like
Sohil Newa retweeted
Petar Veličković Sep 17
As requested , here are a few non-exhaustive resources I'd recommend for getting started with Graph Neural Nets (GNNs), depending on what flavour of learning suits you best. Covering blogs, talks, deep-dives, feeds, data, repositories, books and university courses! A thread 👇
Reply Retweet Like
Sohil Newa retweeted
Kai Arulkumaran Sep 13
Been chatting to a few 3rd year UK STEM PhD students about finishing up, so here's my take Your thesis can be like a few high school science reports - in that you follow the scientific method, negative results are fine, and it doesn't need to change the world.
Reply Retweet Like
Sohil Newa retweeted
Amit Chaudhary Sep 8
I transitioned from software-engineering to data science a year ago. One important factor that helped me was doing small-chunks(>=30min) of learning daily. And logging your learning journey in public. Here is mine:
Reply Retweet Like
Sohil Newa retweeted
Shreya Shankar Sep 4
Beginning a thread on the ML engineer starter pack (please contribute): - ”example spark config” stackoverflow post - sklearn documentation - hatred for Airflow DAGs - awareness of k8s and containers but no idea how to actually use them - “the illustrated transformer” blog post
Reply Retweet Like
Sohil Newa retweeted
Lena Voita Sep 4
NLP Course | For You - interactive lectures-blogs, research thinking exercises and related papers with summaries. And fun! These are not just course materials - this is something developed specially for you (yes, you!) out there.
Reply Retweet Like
Sohil Newa retweeted
Michael A Osborne Aug 24
At the start of my PhD, I had a research question. After my 1st year, I realised that that question was too hard—I picked a simpler one. After my 2nd year, I realised that _that_ question was too hard—I picked a trivial one. I'm still going on that trivial question. 12 years on.
Reply Retweet Like
Sohil Newa retweeted
Sanny Kim Aug 14
Everyone has heard about 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
Reply Retweet Like
Sohil Newa Aug 3
Doing NLP Specialization by and a fellow nepali blogger’s tweet is used as an example.
Reply Retweet Like
Sohil Newa retweeted
Alexander Clark Jul 23
This paper has been a long time cooking, but it's out now in TACL, with Nathanaël Fijalkow. Pretty much the first nontrivial (consistent) algorithm for learning Probabilistic Context-Free Grammars: 1/5
Reply Retweet Like
Sohil Newa retweeted
👩‍💻 Paige Bailey @ 127.0.0.1 🏠 Jul 21
"Byteboard replaces the old-fashioned [interview] process with an identity-blind, project-based evaluation process that highlights real-world skills that will be used on the job, in real-world coding environment." Good job, . ♥️ H/T
Reply Retweet Like
Sohil Newa retweeted
👩‍💻 Paige Bailey @ 127.0.0.1 🏠 Jul 21
✨📄 Are you intending to submit a publication for review at an upcoming academic conference? This deck from 's Bill Freeman is an excellent guide: It irks me that these practices are not universally taught in *all* undergraduate & graduate schools.
Reply Retweet Like
Sohil Newa retweeted
elvis Jul 21
I get this question a lot: "I want to get started with deep learning, which papers should I start reading?" This repo contains a nicely curated list of deep learning papers for different areas where deep learning is applied.
Reply Retweet Like
Sohil Newa retweeted
👩‍💻 Paige Bailey @ 127.0.0.1 🏠 Jul 20
👩‍💻 Full disclosure: I detest whiteboard interviews. But: offers a course each year called "problem-solving for the CS Technical Interview", and if you want to pass whiteboard exams at FAANG companies, it is *the best* resource. Link here: 👉
Reply Retweet Like
Sohil Newa retweeted
Segun Adebayo Jul 18
📝 Lessons learned today: As a Software engineer, learning how to introduce yourself and communicating what you do clearly can make a lot of difference in your career. If you ever need to talk about yourself via DM or email, here are 4 tips I discovered: 👇🏼 Thread
Reply Retweet Like
Sohil Newa retweeted
Thomas Kipf Jul 16
I will be talking about Relational Structure Discovery today at the Graph Representation Learning (and Beyond) workshop at ICML. The talk will be live-streamed at 9:30 CEST. Join us (w/ ) for live Q&A after the talk! Slide credit:
Reply Retweet Like
Sohil Newa Jul 14
"NLP is hard". Attending NLP for social good session at hosted by
Reply Retweet Like