first they do it as part of their job then they do it as a stepping stone then it wins
MACHINE LEARNING
-
Data Quality and Curriculum Learning for LLM Training
By
–
"Obviously anything that looks useless (like SHA hashes or other noise) is not worth training on and is just wasting training capacity and time"
"You may want to start with simpler topics and work up to more complex later, just like in human school" -
GPT Training Framework with Dataset and Sampling Tools
By
–
Prompt: "You are a GPT and you're in charge of training an even better GPT, congrats! You have a dataset here . You can train it on document chunks like this: and sample its current understanding like this: . And here's a calculator and a scratchpad . Begin:"
-
Meta-learning policies for LLM attention management during training
By
–
Feels like a lot of fertile ground is left in managing the "attention" of an LLM during its training via a meta-learning policy, instead of the typical "memorize dataset uniformly at random" strategy. And giving it a calculator and a scratch pad.
-
Training Strategies: Skimming, Filtering Noise, and Revisiting Content
By
–
More generally a few remarkable strategies people use during their training:
1) skim text because they already know it
2) ignore text because it's clearly noise (e.g. they won't memorize SHA256 hashes. LLMs will.)
3) revisit parts that are learnable but not yet learned -
Examples vs. Presentations: Spaced Repetition in LLM Training
By
–
Is it the number of examples that matters or the number of presentations to the model during training? E.g. humans used spaced repetition to memorize facts but there are no equivalents of similar techniques in LLMs where the typical training regime is uniform random.
-
AI and Machine Learning Combat $300B Annual Insurance Fraud
By
–
Insurance fraud in the US is a $300 billion per year problem. Learn how @Quantiphi and NVIDIA are using #AI and #machinelearning for document digitization to identify risks, prevent fraud, and accelerate claims processing. Register today: https://
nvda.ws/3GkfXwO -
Galática’s fastai notebook plan exploration attempt
By
–
Looks like http://
galatica.org had a good plan for a fastai notebook, although I can't get it to go further than producing this intro! 😀 -
MLOps Maturity Model: Maximizing Your Data Science ROI
By
–
Where does your company fit on this #MLOps Maturity Model? And what could that mean for your ROI on datascience investments? Check out @JoshPoduska
's blog to find out: -
Robot Dog Walks on Stools Using Onboard Vision
By
–
New work from @berkeley_ai and @CMU_Robotics on visual locomotion enables a robot dog walking on tall bar stools in @ashishkr9311's living room — entirely from onboard cameras and compute. Trained in simulation and deployed directly in the real world!https://t.co/kBEpOCsRob https://t.co/wVIeiMgfd2
— Berkeley AI Research (@berkeley_ai) 15 novembre 2022New work from @berkeley_ai and @CMU_Robotics on visual locomotion enables a robot dog walking on tall bar stools in @ashishkr9311
's living room — entirely from onboard cameras and compute. Trained in simulation and deployed directly in the real world! http://
vision-locomotion.github.io