I added more FREE downloadable resources for my @X Subscribers today. 2200+ resources are now available for subscribers to my @X account. Subscribe for only US$4.99/month #MachineLearning #AI #EdgeAI #DataScience #Python #Mathematics #Statistics #SQL #GenAI #IoT #ML
MACHINE LEARNING
-
AI Model Improves Traffic Predictions for Smarter Cities
By
–
Congested streets impact our economies, the environment, & our collective well-being — to build smarter cities, we need a quantitative understanding of traffic. Read more about a new model that improves traffic predictions on roadways with limited data →
https://
goo.gle/4fR9JTC -
Power Analysis: Detecting Minimum Effects Between AI Models
By
–
Recommendation #5: Use power analysis Statistical power refers to the ability to detect a hypothetical difference, assuming it exists. Our paper develops formulas for determining the Minimum Detectable Effect between two models, two prompts, or two sets of hyperparameters.
-
Statistical Framework for Model Evaluation in AI
By
–
Beyond these specific recommendations, our work provides an overarching framework for thinking about model evaluations in a statistical way. Read the full paper here:
-
Clustered Standard Errors for AI Evaluation Methodology
By
–
Recommendation #2: Cluster standard errors Many evaluations (esp. reading-comprehension evals) include questions that are clustered together. These question clusters violate an assumption of the Central Limit Theorem—but they are a natural fit for clustered standard errors.
-
Central Limit Theorem for AI Evaluation Score Reporting
By
–
Recommendation #1: Use the Central Limit Theorem Evaluation scores are usually mean scores across a large number of questions. This is a perfect fit for the Central Limit Theorem. In the paper, we suggest reporting the CLT-based standard errors alongside mean scores.
-
Evaluation Questions Distribution Theory and Core AI Recommendations
By
–
Our key assumption? We imagine that evaluation questions are randomly drawn from an underlying distribution of questions. This assumption unlocks a rich theoretical landscape, from which we derive five core recommendations.
-
BF16 Weights and Rate Limits Discussion
By
–
We run bf16 – the same weights that you see in the model repo. Re: rate limits:
-
AI monitoring species changes globally using acoustics and remote sensing
By
–
MIT assistant professor Sara Beery on how her research group applies AI to monitor how species are changing around the world, including using tools like acoustics, sonar, & remote sensing data.
— MIT CSAIL (@MIT_CSAIL) 19 novembre 2024
Full video: https://t.co/AIjVJlwQ6b pic.twitter.com/90OkbWaG4yMIT assistant professor Sara Beery on how her research group applies AI to monitor how species are changing around the world, including using tools like acoustics, sonar, & remote sensing data. Full video: https://
bit.ly/3ANNqiR -
Being Addicted To Generative AI
By
–
Being Addicted To Generative AI
#AI #AIio #BigData #ML #NLU #Futureofwork @chrismessina @ChristopherIsak @davidwkenny @debashis_dutta @petitegeek @fabiomoioli @GaryMarcus @asokan_telecom