Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
Înapoi la articole →

Scientific Memo

science-memo.blogspot.com/atom.xml
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 25

  1. Why the simplest explanation is always the best

    (Scientific Memo)

    Preamble The simplest explanation is always the best among the explanations that are representative.

  2. Compressive algorithmic randomness: Gibbs-randomness proposition for massively energy efficient deep learning

    (Scientific Memo)

    Figure: Dual Tomographic Compression Performance, Süzen, 2025.Preamble Randomness is elusive and its probably one of the outstanding concepts for human scientific endeavour, along with gravity.

  3. Ultimate physical limit of data storage: Connecting Bekenstein Bound to Landauer Principle

    (Scientific Memo)

    Preamble Bekenstein's Information (Wikipedia) Black holes are not too esoteric anymore after LIGO's success and successful imaging efforts.

  4. Basic understanding of a metric tensor: Disassemble the concept of a distance over Riemannian Manifolds

    (Scientific Memo)

    Preamble Gaussian Curvature (Wikipedia) One of the core concepts in Physics is so called metric tensor.

  5. Mathematical Definition of Heuristic Causal Inference: What differentiates DAGs and do-calculus?

    (Scientific Memo)

    Preamble David Hume (Wikipedia) Experimental design is not a new concept and randomised control trials (RCTs) are our solid gold standard of doing quantitative research, when no apparent physical laws are available to validate observations.

  6. Resolution of misconception of overfitting: Differentiating learning curves from Occam curves

    (Scientific Memo)

    Preamble Occam (Wikipedia) A misconception that overfitted model can be identified with the amount of generalisation gap between model's training and test sets over its learning curves is still out there.

  7. Loschimidt's Paradox and Causality: Can we establish Pearlian expression for Boltzmann's H-theorem?

    (Scientific Memo)

    Boltzmann (Wikipedia) Post covers the papers: H-theorem do-conjecture, M.

  8. Insights into Bekenstein entropy with an intuitive mathematical definitions: A look into Thermodynamics of Black-holes

    (Scientific Memo)

    Jacob Bekenstein (Wikipedia) Preamble Thermodynamics of black holes has appeared as one of the most interesting areas of research in theoretical physics [Wald1994], specially after LIGO's massive success.

  9. Misconceptions on non-temporal learning: When do machine learning models qualify as prediction systems?

    (Scientific Memo)

    Preamble Babylonian Tablet for square root of 2.

  10. The concept of overgeneralisation and goodness of rank : Overfitting is not about comparing training and test learning curves

    (Scientific Memo)

    Preamble Walt Disney Hall, Los Angeles (Wikipedia) Unfortunately, it is still thought in machine learning classes that overfitting can be detected by comparing training and test learning curves on the single model's performance.

  11. The conditional query fallacy: Applying Bayesian inference from discrete mathematics perspective

    (Scientific Memo)

    Preamble The Tilled Field, Joan Miró (Wikipedia) One of the core concepts in data sciences is conditional probabilities, $p(x|y)$ appear as logical description of many of the tasks, such as formulating regression or as a core concept in Bayesian Inference.

  12. Differentiating ensembles and sample spaces: Alignment between statistical mechanics and probability theory

    (Scientific Memo)

    Preamble Sample space is the primary concept introduced in any probability and statistics books and in papers.

  13. Overfitting is about complexity ranking of inductive biases : Algorithmic recipe

    (Scientific Memo)

    Preamble Figure: Moon patterns human brain invents.

  14. Heavy-matter-wave and ultra-sensitive interferometry: An opportunity for quantum-gravity becoming an evidence based research

    (Scientific Memo)

    Solar Eclipse of 1919 (wikipedia) Preamble Cool ideas in theoretical physics are ofter opaque for general reader whether if they are backed up with any experimental evidence in the real world.

  15. Building robust AI systems: Is an artificial intelligent agent just a probabilistic boolean function?

    (Scientific Memo)

    Preamble George Boole (Wikipedia) Agent, AI agent or an intelligent agent is used often to describe algorithms or AI systems that are released by research teams recently.

  16. Bayesian rabbit holes: Decoding conditional probability with non-commutative algebra

    (Scientific Memo)

    Preamble The White Rabbit (Wikipedia) A novice analyst or even experienced (data) scientist would have thought that the bar notation $|$ in representing conditional probability carries some different operational mathematics.

  17. Empirical risk minimization is not learning : A mathematical definition of learning and re-understanding of overfitting and Occam's razor in machine learning

    (Scientific Memo)

    Simionescu Function (Wikipedia) Preamble The holy grail of machine learning appears to be the empirical risk minimisation.

  18. A misconception in ergodicity: Identify ergodic regime not ergodic process

    (Scientific Memo)

    Preamble Figure 1: Two observable's approach to ergodicity for Bernoulli Trials.

  19. Physics origins of the most important statistical ideas of recent times

    (Scientific Memo)

    Figure: Maxwell's handwritings, state diagram (Wikipedia) Preamble The modern statistics now move into an emerging field called data science that amalgamate many different fields from high performance computing to control engineering.

  20. Periodic Spectral Ergodicity Accurately Predicts Deep Learning Generalisation

    (Scientific Memo)

    Preamble Dali (1931), The Persistence of Memory (Wikipedia) One of the new mathematical concepts arise due to understanding of deep learning is called periodic spectral ergodicity (PSE).

  21. Deep Learning in Mind a Gentle Introduction to Spectral Ergodicity

    (Scientific Memo)

    Preamble Figure: Monalisa on Eigenvector grids (Wikipedia) In the post, A New Matrix Mathematics for Deep Learning : Random Matrix Theory of Deep Learning, we have outlined a new mathematical concepts that are aimed at deep learning but in general belongi…

  22. A New Matrix Mathematics for Deep Learning : Random Matrix Theory of Deep Learning

    (Scientific Memo)

    Preamble Figure: Definition of Randomness (Compagner 1991, Delft University) Development of deep learning systems (DLs) increased our hopes to develop more autonomous systems.

  23. On the fallacy of replacing physical laws with machine-learned inference systems

    (Scientific Memo)

    Preamble Progress in machine learning, specifically so-called deep learning, last decade was astonishingly successful in many areas from computer vision to natural language translation reaching automation close to human-level performance in narrow areas,…

  24. Shifting Modern Data Science Forward: Dijkstra principle for data science

    (Scientific Memo)

    Kindly reposted to KDnuggets by Gregory Piatetsky-Shapiro with the title Data science is not about data -applying Dijkstra principle to data science and enhancements.

  25. Computable function analogs of natural learning and intelligence may not exist

    (Scientific Memo)

    Optimal learning : Meta-optimization Many papers directly equate “machine” learning problem, algorithmic learning oppose to human or animal learning, with optimisation problem.