Tabular machine learning summarized in a visual diagram! h/t @abacusai
MACHINE LEARNING
-
Latest AI Research: Web Crawling and Sorting Algorithms
By
–
From distributed web crawling and selection algorithms to sorting algorithms, find out all about the latest research happening in the AI world here: https://
bit.ly/3iQiF40 @jeevprabnivash @_DigitalIndia @GoI_MeitY @nasscom @NeGD_GoI -
RLHF preference for direct answers over clarifying questions
By
–
I suspect this is because of RLHF — if the goal is to choose responses a human would rank highly against other options, “Could you please clarify X?” or “Am I understanding right that you want Y?” are not usually major contenders for top place.
-
AI-Guided Methods Discover New Nanostructures at Brookhaven Lab
By
–
Did you know that AI-guided autonomous methods can discover new materials like nanostructures? Tap here to know the startling discoveries made by scientists at the US Department of Energy's Brookhaven National Laboratory: https://
bit.ly/3XS5A8O -
Image models prompting: associative bag of labels
By
–
I don’t know much about image models, but prompting them seems very different. It’s more of an associative bag of labels than a text.
-
Minimal AI Stack: Converting Real-World Issues to Mathematical Code
By
–
The core idea of Minimal AI stack is to convert real-world issues into mathematical formulations and then computer codes. Find out more on how this revolutionary stack can design solutions for us: https://
bit.ly/3D6OnAL -
ConvNets Remain Superior Due to Parallelism Advantages
By
–
Nope, convnets are still better due to parallelism. @ylecun probably just made his recommendation based on parallel computation and hardware.
-
Request for LLM Metrics Spreadsheet Comparison Table
By
–
AI Twitter, request for help: 1-2 weeks ago I saw someone tweet out a spreadsheet/table of all known LLMs with details like parameter size, FLOPs, and other quantitative metrics. Basically an updated version of this 2021 "AI and Memory Wall" post below. I can't find it. Help?
-
LSTM Paper Citation Growth: From Obscurity to 100K Citations
By
–
LSTM paper had ~50 citations from 1997 until 2014 when the seq2seq paper made it quite popular (approaching 100K) now. Hang in there ; )
-
Mobile Robotics Course from University of Michigan with Videos and Code
By
–
Mobile Robotics – University of Michigan, 2022 A course that covers maths and algorithms behind state-of-the-art robotic systems. Lecture videos: https://
youtube.com/playlist?list=
PLdMorpQLjeXmbFaVku4JdjmQByHHqTd1F
… Github: https://
github.com/UMich-CURLY-te
aching/UMich-ROB-530-public
…