@forkkr
 United States
Joined July 2013
  • Tweets92
  • Following722
  • Followers41
4Media
As @NeurIPSConf #NeurIPS2021 deadline approaches, I've consolidated some technical writing tips. Succinct answers to each of the questions, Voila, you have a crisp Introduction! Expand on prior work, intuition/tech details, & expts for the rest ensuring the why is always clear
12
196
13
920
Kashob Roy retweeted
Amit Roy@AmitRoy77813 Apr 2021
Thanks for featuring our paper. @forkkr @aminahsanali @Graph_NN #GNN
arXiv Daily
@Arxiv_Daily2 Apr 2021
SST-GNN: Simplified Spatio-temporal Traffic forecasting model using Graph Neural Network deepai.org/publication/sst-g… by @AmitRoy7781 et al. #RecurrentNeuralNetwork #NeuralNetwork

DeepAI

Artificially intelligent tools for naturally creative humans.

deepai.org
1
The recording of my talk on Theoretical Foundations of Graph Neural Networks is now live (+slides in desc.)! 🕸️ Join me as I derive GNNs from first principles, motivate their use in the sciences, and explain how they emerged along several research lines. youtube.com/watch?v=uF53xsT7…
11
250
24
1,110
📘 The draft 2021 edition of Kevin Murphy's comprehensive machine learning book is out now. Along with a shiny new graph embeddings section (V.23) wonderfully curated by @phanein! Should be a wonderful read :) probml.github.io/pml-book/bo…
29
1
149
Kashob Roy retweeted
Kirk Borne
@KirkDBorne2 Jan 2021
997-page book "Dive into #DeepLearning" teaches the ideas, #mathematics, and #coding that power it. Learn more: bit.ly/3nbWf9c ★★★★FREE Download: d2l.ai/d2l-en.pdf #BigData #DataScience #AI #MachineLearning #Algorithms #NeuralNetworks #DataScientists #Python
73
1
157
Hey Old/New Followers👋 This tweet is a thread of every important/useful Threads I have ever tweeted🧵 I guess I have a useful thread for everyone (Specially programmers) Check it out and share with others if you feel like it is useful. 🧵👇
13
61
9
291
Being wrong is not a bad thing like they teach you in school. It is an opportunity to learn something. There are no mistakes, only lessons. Growth is a process of trial and error. 🧠
34
1,429
166
6,980
Kashob Roy retweeted
Santiago
@svpino10 Dec 2020
Free course on Machine Learning taught by Tom Mitchel and Maria-Florina Balcan. ▫️ You get all the notes ▫️ You get all the videos ▫️ Tom and Maria are amazing Course: cs.cmu.edu/~ninamf/courses/6… Just like attending Carnegie Mellon University. For free! From home!
18
298
27
1,167
Kashob Roy retweeted
Bryan Perozzi@phanein5 Dec 2020
Our group @GoogleAI put together 4 hours of content on our work in scalable graph mining and graph learning for a #NeurIPS2020 EXPO workshop this year! You can watch it tomorrow live with us, or view it at your leisure. (Expo reg. is free) Enjoy! gm-neurips-2020.github.io/
4
26
1
148
If you'd like to know more about how we use JAX (empowered by Haiku, Jraph et al.) to accelerate our research @DeepMind, the following blog-post is very informative, and covers a lot of useful (open-sourced!) tools: deepmind.com/blog/article/us…

Using JAX to accelerate our research

DeepMind engineers accelerate our research by building tools, scaling up algorithms, and creating challenging virtual and physical worlds for training and testing artificial intelligence (AI)...

deepmind.google
1
14
87
Proud to share Jraph, our graph neural nets library for #JAX! 🦒 We provide extensive utilities for working with graphs, an elaborate 'GNN model zoo', several examples (incl. OGB), and do not dictate coding style (fully compatible with Flax, Haiku, etc.) github.com/deepmind/jraph

GitHub - google-deepmind/jraph: A Graph Neural Network Library in Jax

A Graph Neural Network Library in Jax. Contribute to google-deepmind/jraph development by creating an account on GitHub.

github.com
3
44
2
255
I finally watched all the talks I wanted to, ended up importing 56 papers to my bib, and now present to you: 🎉 My 13 favorite papers (sorted alphabetically) at #EMNLP2020! 🔥 [1/15]
6
121
14
634
[1/11] Recently, I got a question about which machine learning seminars/reading groups are open to the public. I couldn't find a list, so I decided to create one. It's great to see that there are so many! 📖🧵👇
18
294
34
1,072
Kashob Roy retweeted
Santiago
@svpino21 Nov 2020
A plan to get a job as a Machine Learning Engineer. 🧵👇
38
380
54
2,119
Sharing my lecture slides on "Recent Developments of Graph Network Architectures" from my deep learning course. It is a review of some exciting works on GNNs published in 2019-2020. #feelthelearn rb.gy/quo3n6
11
240
21
1,215
Are you trying to visualize your deep network just 2 days before the #CVPR2021 deadline? Here are some pretty alternatives to boring tensorboard graphs. (1/n)
5
202
26
767
Are you ready to read ~1,900 machine learning papers in the new #NeurIPS2020 proceedings (preliminary version): papers.neurips.cc/paper/2020
Advances in Neural Information Processing Systems 33 pre-proceedings (NeurIPS 2020)

ALT Advances in Neural Information Processing Systems 33 pre-proceedings (NeurIPS 2020)

5
71
7
299
Thanks to an amazing team of authors, we've just posted the official @TensorFlow Lite Micro paper on Arxiv: arxiv.org/pdf/2010.08678.pdf Lots of juicy details about the design and tradeoffs involved, what worked and what didn't!
2
59
7
202
Kashob Roy retweeted
spacy
@dosco9 Oct 2020
Replying to @janexwang
I'm building 42papers.com as a way find the top trending DL/ML/CS papers to read and to collaborate and share notes.
1
1
7
Kashob Roy retweeted
ICLR@iclr_conf8 Oct 2020
3000+ #ICLR2021 submissions reached - we thank authors and the amazing @iclr_conf community as we reach this milestone. Read reflections from the program committee in our first blog post: link.medium.com/Bps5owynpab

3,000+ Submissions Received. Let the Reviewing Begin!

3,000+ Submissions Received. Let the reviewing begin!

link.medium.com
1
28
4
171
Load more