Looking forward to joining @sophiamyang 's
DS/ML book club tomorrow over lunch (1 pm CT) to talk & discuss Machine Learning Q and AI (
https://
leanpub.com/machine-learni
ng-q-and-ai/
…)! This book is a bit more advanced than my previous ones, covering concepts such as – Multi-GPU training paradigms.
MACHINE LEARNING
-
Joining DS/ML Book Club Discussion on Machine Learning and AI
By
–
-
Scaling LLMs with Transformers Alternative Methods
By
–
"How to scale LLMs better with an alternative to transformers" https://
hazyresearch.stanford.edu/blog/2023-07-2
5-m2-bert
… -
Tie-breaking fix improves nearest neighbor classification accuracy to 71.91%
By
–
Small update: In the orig code example in the paper, tie breaking was based on the lowest class label index, i.e., it was biased towards class 0. When I fixed the tie-breaking to select the closest neighbor, I could get a 70.05% -> 71.91% improvement (
https://
github.com/rasbt/nn_plus_
gzip
…). -
Valence and Recursion Launch AI-Driven Drug Discovery Platform
By
–
Exciting to see the birth of a new large-scale effort to weave AI, biology, chemistry and drug discovery together. Valence x Recursion driving what you might call DeepMind/OpenAI for bio+chem
-
Geometric Deep Learning Masterclass: From Euclid to Drug Design
By
–
🔎 For a masterclass on geometric deep learning – from Euclid to drug design – catch @mmbronstein, @GoogleDeepMind Professor at @UniofOxford at @raais.
— Nathan Benaich (@nathanbenaich) 27 juillet 2023
YouTube link below too! pic.twitter.com/V7If66JYzTFor a masterclass on geometric deep learning – from Euclid to drug design – catch @mmbronstein
, @GoogleDeepMind Professor at @UniofOxford at @raais
. YouTube link below too! -
Understanding Large Language Models
By
–
Understanding Large Language Models https://
bit.ly/3BJHYKC #AI #MachineLearning #DeepLearning #LLMs #DataScience -
IROS Conference and Machine Learning Workshop Discussion
By
–
Yes, would love to discuss and will be at IROS! Somewhat relatedly I'll be participating in this workshop next month, maybe some intersections? https://
lbit2023.lst.uni-saarland.de/index.html See you in Detroit! -
In-Context Learning Mechanisms in Transformers Explained
By
–
The mechanisms of in-context learning in transformers are not currently well understood. Visit the #ICML2023 Google Research booth today at 3:30 PM for a demonstration on how a type of gradient descent enables transformers to pay better attention to their context.
-
Meta AI Research Paper Wins ICML 2023 Outstanding Paper Award
By
–
We’re honored to share that Learning-Rate-Free Learning by D-Adaptation, a paper by Meta AI research scientist @aaron_defazio & @konstmish was selected as an #ICML2023 Outstanding Paper! More details and a link to the paper
-
DIDACT: Google’s Dynamic Integrated Developer Activity Model
By
–
Read more about what @DynamicWebPaige
's discussing: DIDACT (Dynamic Integrated Developer ACTivity) https://
ai.googleblog.com/2023/05/large-
sequence-models-for-software.html
…