[Updated! 461-page PDF eBook] Physics-based Deep Learning: https://
arxiv.org/abs/2109.05237
+
Learn more at: https://
physicsbaseddeeplearning.org/intro.html ——————
#AI #MachineLearning #ML #DataScience #NeuralNetworks #Algorithms #Mathematics #DataScientist
RESEARCH
-
Physics-based Deep Learning eBook (arXiv)
By
–
-
Downloadable 284‑page Introduction to Neural Networks
By
–
Download 284-page PDF “Introduction to #NeuralNetworks” https://
dkriesel.com/en/science/neu
ral_networks
…
—————
#DataScience #AI #Algorithms #ML #MachineLearning #DeepLearning #Mathematics #Calculus #DataScientist -
Mathematical Theory of Deep Learning — arXiv Paper and Book
By
–
Mathematical Theory of #DeepLearning [download 333-page PDF]: https://
arxiv.org/abs/2407.18384 *UPDATED*
+ +
See also this book: http://
amzn.to/3BqaW5e
—————
#AI #DataScience #ML #MachineLearning #Calculus #DataScientist #Mathematics #Algorithms -
AI had soul two years ago but was in infancy
By
–
AI had soul already 2 years ago, but it was infancy
-
Ingenium publishes fault detection paper for induction motors
By
–
@ingenium_rg publishes new paper on fault detection in induction motors. Our study combines Wavelet Transform & Artificial Neural Networks, achieving 96% accuracy in predicting stator faults. link.springer.com/chapter/10… #Engineering #FaultDetection #AI #Ingenium @faustospain
→ View original post on X — @faustospain, 2026-02-24 11:01 UTC
-
AI mimics devs but lacks real expertise
By
–
When you say "act as a senior developer" the model doesn't think like one. It writes like one. Big difference. It pattern-matches to how developers sound in training data. Not how they actually solve problems. You get confident-sounding output. Not expert-level thinking.
-
Developing New Theories with Pre-Theory Data: A Paradox
By
–
Brilliant idea. Very thought provoking. How do we develop a new theory by training a model only with data prior to the existence of that theory?
— Nando de Freitas (@NandoDF) 24 février 2026
Theory could also be a capability, like language itself or logical reasoning. https://t.co/LLsC1Q24EtBrilliant idea. Very thought provoking. How do we develop a new theory by training a model only with data prior to the existence of that theory? Theory could also be a capability, like language itself or logical reasoning.
-
Bayesian Methods for Hackers — Probabilistic Programming Resource
By
–
Bayesian Methods for Hackers — Probabilistic Programming and Bayesian Inference: http://
amzn.to/2Ni4xOz
—————
#MachineLearning #DataScience #ML #AI #Statistics #DataScientist -
The Relationship Between AI Progress and Real-World Impact
By
–
A tale of two S-curves: AI impact picks up even as AI progress slows down.
-
ExomeBench: AI Benchmark for Disease-Associated Genetic Variants
By
–
Introducing ExomeBench: a benchmark for evaluating genomic models on disease-associated genetic variants, built in collaboration with with @MayoClinic
. Most genomics benchmarks focus on general sequence modeling tasks. What remains under-evaluated is whether these models can