Samuel Situmeang

[Samuel Situmeang @exemuel]

Real progress requires us to think like geologists and take the "long view." 🌱
Instead of complaining, let's focus on what truly changes the future: Imagination, Ambition, and Education.
Highly recommend this brilliant conversation with pak @GitaWirjawan: https://t.co/i8zrSfx6cA

[Samuel Situmeang @exemuel]

https://t.co/LiNU56JLez

[Adam Grant @AdamMGrant]

On major life decisions, the purpose of seeking advice is not to get answers. It’s to gain perspective.

No one knows what's best for you. They can only share what makes sense to them.

The most important question to ask is not what you should do. It's what you might be missing.

[Miles Cranmer @MilesCranmer]

Three years ago, I started working on an easy-to-use tool for interpretable machine learning in science. I wanted it to do for symbolic regression what Theano did for deep learning.

Today, I am beyond excited to share with you the paper describing it!
https://t.co/be2cVdukPy

1.

[Dave Richeson @divbyzero]

Cool proof and cool example of using CSS to create mathematical animations on web pages! Here's the page with the math https://t.co/HhInyrIjY5 and here's the page describing the CSS https://t.co/16eoPjxwff.

[Kirk Borne @KirkDBorne]

I love this beautiful and extraordinarily well published book: "Better Data Visualizations" by @jschwabish

Get it at https://t.co/JQGXY00Gfn
——————
#DataViz #DataStorytelling #Statistics #VisualAnalytics #DataScience #DataScientists #BeDataBrilliant

[Massimo @Rainmaker1973]

How a book written in 1910 could teach you calculus better than several books of today

[Calculus Made Easy, by Silvanus P. Thompson, 1910 - full text pdf: https://t.co/W4gspJoGQc or with the table of contents: https://t.co/55dkZAeGmv]

[Andrew Owens @andrewhowens]

I'm looking for PhD students to join me at UMich! You would be part of this wonderful computer vision group: https://t.co/O58mj1FTLk

[Larry Snyder @LarrySnyder610]

So inspired by @CynthiaRudin’s plenary @INFORMS2022 about interpretable AI for high-stakes decisions. Takeaways: 1. Simple transparent models often work as well as complex ML for many decisions. 2. Those models are found using methods based on #optimization.

[Jeremy Cohen @deepcohen]

This amazing paper by Alex Damian, Eshaan Nichani, and Jason Lee is a critical contribution to deep learning theory and optimization theory. The paper contains the key to understanding many surprising aspects of neural net training dynamics, including

https://t.co/8H8i0h2kj4

[Samuel Situmeang @exemuel]

Linked pixel-based visualizations https://t.co/FDIhQdIXeM

[Samuel Situmeang @exemuel]

@fransjhs kadang sesuatu yang panjang (relatif), tidak menarik (relatif), dan tidak mudah dipahami (relatif) itu perlu untuk dibaca.

[eleesa_elise @yiputaelisa]

Ini pegimane nonton tiba2 lapangannya kosong? 😑

[Yann LeCun @ylecun]

OPT-175b:
Open Pre-Trained language model with 175 billion paramaters is now available to the research community.

Blog post: https://t.co/NBacfKGUHC
Paper: https://t.co/tLYUoWisZA
Code + small pre-trained models: https://t.co/M9nLCOf3Rx
(using OPT-175b requires a registration)

[Futurism @futurism]

Terrifying! https://t.co/4aexKUISqJ

[Prashant @itsprasa]

10 Visuals that will change the way you see the world

1.

[Rafael Sommerhalder @Serendippo]

#bubbles

[Samuel Situmeang @exemuel]

@nikomamora Selamat Natal Bang...