What if AI could automatically write and optimize entire GPU programs for your ML workloads? Researchers from the University of Minnesota-Twin Cities introduce StitchCUDA. This multi-agent framework features a Planner, Coder, and Verifier. The Coder uses innovative rubric-based
RESEARCH
-
SGD as ResNet: Rethinking Attention Architecture Fundamentals
By
–
SGD is a ResNet too (the blocks of it are fwd+bwd), the residual stream is the weights so… We're not taking the Attention is All You Need part literally enough? π
-
Developing AGI-Awareness as a Learnable Skill
By
–
> 2) Being AGI-pilled is a skill & you can get better at it can you give more detail/thoughts now?
-

Machine Learning for Time Series: Forecasting, Prediction, Anomaly Detection
By
–
Machine Learning for #TimeSeries with Python β Forecast trends, Predict the future, Detect anomalies with state-of-the-art ML methods: http://
amzn.to/3xf5ZdI by @benji1a ββββββ
#DataScience #AI #Forecasting #PredictiveAnalytics #AnomalyDetection #IoT #IIoT #DataScientist -

Model-Based Clustering and Classification for Data Science in R
By
–
Model-Based Clustering and Classification for Data Science, with Applications in R: http://
amzn.to/4aV1VhH
βββββ
#Rstats #DataScientist #MachineLearning #ML #AI #Statistics #Mathematics -

Data Science for Business: Data Mining and Analytic Thinking Essentials
By
–
Data Science for Business β What You Need to Know about Data Mining and Data-Analytic Thinking: http://
amzn.to/3dRgs18
ββββ
#ML #AI #MachineLearning #DataScientist #Analytics @LeadershipData -

Predictive Statistics: Analysis and Inference Beyond Models
By
–
Predictive #Statistics β Analysis and Inference beyond Models: http://
amzn.to/49TYu9v
βββββ
#Probability #DataScience #Mathematics #MachineLearning #ML #DataScientist -

Mathematical Certainty and Proof: Embracing Uncertainty in Discovery
By
–
Book by @adamjkucharski explains how certainty, even in math, can be an illusion. "Proof: The Art and Science of Certainty" at http://
amzn.to/4m7gm8l #Mathematics "To discover proof [of something], we must reach into a thicket of errors and biases and embrace uncertainty" -
C Compiler to LLM Weights and Logarithmic Attention Innovation
By
–
Wait this is so awesome!! Both 1) the C compiler to LLM weights and 2) the logarithmic complexity hard-max attention and its potential generalizations. Inspiring!
-

Artificial Intelligence for Science: A Deep Learning Revolution
By
–
Artificial Intelligence for Science – A Deep Learning Revolution: http://
amzn.to/457QCTa
