Symphony of high-dimensional brain

Alexander N. Gorban; Ivan Y. Tyukin; Valeri A. Makarov

arxiv: 1906.12222 · v1 · pith:423CBKUGnew · submitted 2019-06-27 · 🧬 q-bio.NC · cs.AI

Symphony of high-dimensional brain

Alexander N. Gorban , Valeri A. Makarov , Ivan Y. Tyukin This is my paper

Pith reviewed 2026-05-25 13:36 UTC · model grok-4.3

classification 🧬 q-bio.NC cs.AI

keywords simplicity revolutionhigh-dimensional brainmachine learning theorycurse of dimensionalityneural ensemblesnon-random distributionsneuroscienceAI

0 comments

The pith

A journal discussion synthesizes expert views on revising machine learning theory for non-random high-dimensional distributions in the brain.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper serves as the closing contribution to a scientific discussion on the simplicity revolution in neuroscience and AI, triggered by an earlier review on small neural ensembles. It collects and examines responses from multiple participants addressing topics such as the gap between theoretical random distributions and extremely non-random real data, along with high-dimensional pitfalls. The analysis identifies possible outcomes for how these ideas could influence research directions in both machine learning and neuroscience. A sympathetic reader would care because the synthesis clarifies where standard modeling assumptions may fail when applied to brain data.

Core claim

By reviewing the collected opinions, the paper shows that the simplicity revolution calls for revisions to common machine learning theory to accommodate the difference between theoretical random distributions and the extremely non-random distributions found in real brain data, while also requiring attention to multiple forms of the curse of dimensionality and high-dimensional pitfalls in neuroscience.

What carries the argument

The symphony of opinions from the discussion participants, which aggregates their responses to map areas of agreement and divergence on the simplicity revolution.

Load-bearing premise

The discussion participants' views are taken as representative enough to draw conclusions about field-wide implications for the simplicity revolution.

What would settle it

A broader survey of machine learning and neuroscience researchers that finds substantially different priorities or concerns would show that the analyzed opinions do not represent the fields.

read the original abstract

This paper is the final part of the scientific discussion organised by the Journal "Physics of Life Rviews" about the simplicity revolution in neuroscience and AI. This discussion was initiated by the review paper "The unreasonable effectiveness of small neural ensembles in high-dimensional brain". Phys Life Rev 2019, doi 10.1016/j.plrev.2018.09.005, arXiv:1809.07656. The topics of the discussion varied from the necessity to take into account the difference between the theoretical random distributions and "extremely non-random" real distributions and revise the common machine learning theory, to different forms of the curse of dimensionality and high-dimensional pitfalls in neuroscience. V. K{\r{u}}rkov{\'a}, A. Tozzi and J.F. Peters, R. Quian Quiroga, P. Varona, R. Barrio, G. Kreiman, L. Fortuna, C. van Leeuwen, R. Quian Quiroga, and V. Kreinovich, A.N. Gorban, V.A. Makarov, and I.Y. Tyukin participated in the discussion. In this paper we analyse the symphony of opinions and the possible outcomes of the simplicity revolution for machine learning and neuroscience.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a discussion summary of a journal exchange on high-dimensional effects in neuroscience and ML, with no new results or analysis.

read the letter

This paper is the closing note to a discussion in Physics of Life Reviews triggered by the review on small neural ensembles in high-dimensional brain. It gathers comments from the listed participants on issues like non-random distributions versus standard ML assumptions, forms of the curse of dimensionality, and possible implications for both fields. The text organizes those comments into themes and notes possible outcomes of the simplicity idea. That organization gives a compact map of what came up in the exchange. If a reader wants a single place to see the range of views without tracking each separate comment, this serves that narrow purpose. The paper does not add original data, derivations, experiments, or even a deeper synthesis. The analysis remains descriptive of the opinions already expressed. Because the piece frames itself as reporting one curated conversation, it does not need to defend statistical representativeness, but it also does not deliver the kind of critical comparison or new framing that would make it stand as independent work. The citation pattern is appropriate and points back to the initiating review. This is mainly of interest to people already following that specific journal discussion or the original review. A reader seeking substantive new evidence or theory on high-dimensional brain phenomena will not find it here. It does not merit peer review as a research paper; it fits the format of a discussion summary or editorial close.

Referee Report

0 major / 2 minor

Summary. This paper is the concluding contribution to a discussion organized by Physics of Life Reviews on the simplicity revolution in neuroscience and AI, initiated by the 2019 review 'The unreasonable effectiveness of small neural ensembles in high-dimensional brain'. It summarizes and analyzes the opinions expressed by the listed participants (V. Kůrková, A. Tozzi and J.F. Peters, R. Quian Quiroga, P. Varona, R. Barrio, G. Kreiman, L. Fortuna, C. van Leeuwen, V. Kreinovich, A.N. Gorban, V.A. Makarov, and I.Y. Tyukin) on topics including differences between theoretical random distributions and real non-random distributions, revisions to machine-learning theory, forms of the curse of dimensionality, and high-dimensional pitfalls in neuroscience, while discussing possible outcomes of the simplicity revolution.

Significance. As a synthesis of a curated expert exchange rather than an original empirical or theoretical contribution, the manuscript provides a consolidated record of viewpoints on high-dimensional challenges in brain modeling and AI. Its value lies in documenting the range of positions within one organized discussion, which may assist readers in navigating the ongoing debate without advancing new claims or generalizations.

minor comments (2)

The abstract and introduction list participants and topics but would benefit from explicit cross-references (e.g., section numbers) to the original discussion contributions to improve traceability for readers.
A concise table or bullet-point summary of the principal positions held by each participant would enhance readability and allow quicker comparison of the 'symphony of opinions'.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of the manuscript and the recommendation to accept. The paper is intended as a synthesis documenting the range of expert viewpoints from the Physics of Life Reviews discussion, which we believe provides value in consolidating the debate on the simplicity revolution without claiming new empirical or theoretical advances.

Circularity Check

0 steps flagged

No circularity; purely descriptive synthesis of external discussion

full rationale

The paper is the concluding commentary on a journal-organized discussion. Its content consists of reporting and analyzing opinions expressed by listed participants (V. Kůrková, A. Tozzi, etc.) on topics initiated by a prior review. No derivations, equations, predictions, fitted parameters, or first-principles claims appear. The text does not invoke uniqueness theorems, self-citations as load-bearing premises, or rename empirical patterns; it remains a straightforward synthesis without any reduction of outputs to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a review-style discussion paper containing no models, derivations, or empirical claims, so the ledger is empty.

pith-pipeline@v0.9.0 · 5756 in / 834 out tokens · 18360 ms · 2026-05-25T13:36:37.306764+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

35 extracted references · 35 canonical work pages · 2 internal anchors

[1]

The unreasonable effectiveness of small neu ral ensembles in high- dimensional brain

K˚ urkov´ a V . Some insights from high-dimensional spheres: Comment on “The unreasonable effectiveness of small neu ral ensembles in high- dimensional brain” by Alexander N. Gorban et al. Phys Life Re v 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.014

work page doi:10.1016/j.plrev.2019.03.014 2019
[2]

The Borsuk-Ulam theorem solves the cu rse of dimensionality: Comment on ”The unreasonable effect ive- ness of small neural ensembles in high-dimensional brain” b y Alexander N

Tozzi A, Peters JF. The Borsuk-Ulam theorem solves the cu rse of dimensionality: Comment on ”The unreasonable effect ive- ness of small neural ensembles in high-dimensional brain” b y Alexander N. Gorban et al. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.04.008

work page doi:10.1016/j.plrev.2019.04.008 2019
[3]

The unreasonable ef- fectiveness of small neural ensembles in high-dimensional brain

V arona P . High and Low dimensionality in Neuroscience an d Artiﬁcial Intelligence: Comment on “The unreasonable ef- fectiveness of small neural ensembles in high-dimensional brain” by A.N. Gorban et al. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.02.008

work page doi:10.1016/j.plrev.2019.02.008 2019
[4]

Brainland

Barrio R. “Brainland” vs. “ﬂatland”: how many dimension s do we need in brain dynamics? Comment on the paper “The unrea son- able effectiveness of small neural ensembles in high-dimen sional brain” by Alexander N. Gorban et al. Phys Life Rev 2019 ; this issue. https://doi.org/10.1016/j.plrev.2019.02.010

work page doi:10.1016/j.plrev.2019.02.010 2019
[5]

The unreasonable effectiveness of small neural ense mbles in high- dimensional brain

Kreiman G. It’s a small dimensional world after all: Comm ent on “The unreasonable effectiveness of small neural ense mbles in high- dimensional brain” by Alexander N. Gorban et al. Phys Life Re v 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.015

work page doi:10.1016/j.plrev.2019.03.015 2019
[6]

The unreasonable effectiveness of small neural ensembles in high-dimension al brain

Fortuna L. Nonlinear effects for the reinforcement of sm all neural ensembles in high dimensional brain: Comment on “ The unreasonable effectiveness of small neural ensembles in high-dimension al brain” by A.N. Gorban, V .A. Makarov, I.Y . Tyukin. Phys Lif e Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.004

work page doi:10.1016/j.plrev.2019.03.004 2019
[7]

The unreasonable effectiveness of small neural ensembles in high-dimensional brain

V an Leeuwen C. The reasonable ineffectiveness of biolog ical brains in applying the principles of high-dimensional cybernetics: Comment on “The unreasonable effectiveness of small neural ensembles in high-dimensional brain” by Alexander N. Gorban et al. Phy s Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.005

work page doi:10.1016/j.plrev.2019.03.005 2019
[8]

Akakhievitch revisited: Comment on ”Th e unreasonable effectiveness of small neural ensembles in h igh-dimensional brain” by Alexander N

Quian Quiroga R. Akakhievitch revisited: Comment on ”Th e unreasonable effectiveness of small neural ensembles in h igh-dimensional brain” by Alexander N. Gorban et al. Phys Life Rev 2019; this i ssue. https://doi.org/10.1016/j.plrev.2019.02

work page doi:10.1016/j.plrev.2019.02 2019
[9]

The heresy of unheard-of simplicity: Comm ent on ”The unreasonable effectiveness of small neural en- sembles in high-dimensional brain” by A.N

Kreinovich V . The heresy of unheard-of simplicity: Comm ent on ”The unreasonable effectiveness of small neural en- sembles in high-dimensional brain” by A.N. Gorban, V .A. Mak arov, and I.Y . Tyukin. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.04.006

work page doi:10.1016/j.plrev.2019.04.006 2019
[10]

Paris: Gauthier-Villars, 1951

L´ evy P .Probl` emes concrets d’analyse fonctionnelle. Paris: Gauthier-Villars, 1951

work page 1951
[11]

An Elementary Introduction to Modern Convex Geometry

Ball K. An Elementary Introduction to Modern Convex Geometry. Flavors of Geometry, V ol. 31. Cambridge, UK: MSRI Publications; 1997. https://doi.org/10.1007/BF02699376

work page doi:10.1007/bf02699376 1997
[12]

Concentration of measure and isoperimetr ic inequalities in product spaces

Talagrand M. Concentration of measure and isoperimetr ic inequalities in product spaces. Publications Mathematiques de l’IHES 1995;81:73– 205

work page 1995
[13]

Probabilistic Bounds for Binary Classiﬁcation of Large Data Sets

K˚ urkov´ a V , Sanguineti M. Probabilistic Bounds for Binary Classiﬁcation of Large Data Sets. In: Oneto L, Navarin N , Sperduti A, Anguita D. (eds) Recent Advances in Big Data and Deep Learning. INNSBDD L 2019. Proceedings of the International Neural Networks So ciety, vol 1. Springer, pp. 309–319. https://doi.org/10.1007/978-3-030-16841-4_32

work page doi:10.1007/978-3-030-16841-4_32 2019
[14]

Stochastic separation theorems

Gorban AN, Tyukin IY . Stochastic separation theorems. Neural Netw. 2017;94:255–259. https://doi.org/10.1016/j.neunet.2017.07.014

work page doi:10.1016/j.neunet.2017.07.014 2017
[15]

Augmented Artificial Intelligence: a Conceptual Framework

Gorban AN, Grechuk B, Tyukin IY . Augmented Artiﬁcial In telligence: a Conceptual Framework, arXiv preprint 2018, a rXiv:1802.02172 [cs.AI]. https://arxiv.org/abs/1802.02172

work page internal anchor Pith review Pith/arXiv arXiv 2018
[16]

C orrection of AI systems by linear discriminants: Probabili stic foundations

Gorban AN, Golubkov A, Grechuk B, Mirkes EM, Tyukin IY . C orrection of AI systems by linear discriminants: Probabili stic foundations. Inf. Sci. 2018; 466:303-22. https://doi.org/10.1016/j.ins.2018.07.040

work page doi:10.1016/j.ins.2018.07.040 2018
[17]

The unreasonable effe ctiveness of small neural ensembles in high-dimensional br ain

Gorban AN, Makarov V A, Tyukin IY . The unreasonable effe ctiveness of small neural ensembles in high-dimensional br ain. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2018.09.005

work page doi:10.1016/j.plrev.2018.09.005 2019
[18]

Observed universality of phase tran sitions in high-dimensional geometry, with implications f or modern data analysis and signal processing

Donoho D, Tanner J. Observed universality of phase tran sitions in high-dimensional geometry, with implications f or modern data analysis and signal processing. Phil. Trans. R. Soc. A 2009;367:4273 –4293. https://doi.org/10.1098/rsta.2009.0152

work page doi:10.1098/rsta.2009.0152 2009
[19]

Principal manifolds and graphs i n practice: from molecular biology to dynamical systems

Gorban AN, Zinovyev A. Principal manifolds and graphs i n practice: from molecular biology to dynamical systems. In ternational Journal of Neural Systems 2010;20(03):219–232. https://doi.org/10.1142/S0129065710002383

work page doi:10.1142/s0129065710002383 2010
[20]

(eds.) Principal Manifolds for Data Visualisation and Dimension R eduction

Gorban AN, K´ egl B, Wunsch D, Zinovyev A. (eds.) Principal Manifolds for Data Visualisation and Dimension R eduction. Lecture Notes in Computational Science and Engineering, V ol. 58. Berlin – Heidelberg – New Y ork: Springer, 2008. 4

work page 2008
[21]

Data complexity measured by princ ipal graphs

Zinovyev A, Mirkes E. Data complexity measured by princ ipal graphs. Comput. Mat. Appl. 2013;65(10):1471–1482. https://doi.org/10.1016/j.camwa.2012.12.009

work page doi:10.1016/j.camwa.2012.12.009 2013
[22]

Gorban AN, Tyukin IY , Blessing of dimensionality: math ematical foundations of the statistical physics of data, Ph il. Trans. R. Soc. A 2018;376:20170237. https://doi.org/10.1098/rsta.2017.0237

work page doi:10.1098/rsta.2017.0237 2018
[23]

Single-cell trajectori es reconstruction, exploration and mapping of omics data wi th STREAM

Chen H, Albergante L, Hsu JY , Lareau CA, Bosco GL, Guan J, Zhou S, Gorban AN, Bauer DE, Aryee MJ, Langenau DM, Zinovyev A , Buenrostro JD, Y uan G-C, Pinello L. Single-cell trajectori es reconstruction, exploration and mapping of omics data wi th STREAM. Nature Communications 2019;10:1903. https://doi.org/10.1038/s41467-019-09670-4

work page doi:10.1038/s41467-019-09670-4 2019
[24]

Generalization of a theorem of Lusternik-Schni relman on covering of spheres

Fet AI. Generalization of a theorem of Lusternik-Schni relman on covering of spheres. Dokl. Akad. Nauk SSSR 1954;95 :1149-1152

work page 1954
[25]

The multidimensional brain

Tozzi A. The multidimensional brain. Phys Life Rev 2019 . https://doi.org/10.1016/j.plrev.2018.12.004

work page doi:10.1016/j.plrev.2018.12.004 2019
[26]

Estimating the effective dimension of large biological datasets using Fisher separability analysis

Albergante L, Bac J, Zinovyev A. Estimating the effecti ve dimension of large biological datasets using Fisher sepa rability analysis, 2019, arXiv:1901.06328 [cs.LG]. https://arxiv.org/pdf/1901.06328.pdf

work page internal anchor Pith review Pith/arXiv arXiv 2019
[27]

Laboratory of advanced methods for high-dimensional d ata analysis https://github.com/lamhda

work page
[28]

Discrete Sequential Informat ion Coding: Heteroclinic Cognitive Dynamics

Rabinovich MI, V arona P . Discrete Sequential Informat ion Coding: Heteroclinic Cognitive Dynamics. Front Comput Neurosci 2018;12:73. https://doi.org/10.3389/fncom.2018.00073

work page doi:10.3389/fncom.2018.00073 2018
[29]

Extensions of Lipschitz ma ps into a Hilbert space.Conference in modern analysis and pr obability (New Haven, Conn., 1982), Contemp

Johnson W, Lindenstrauss J. Extensions of Lipschitz ma ps into a Hilbert space.Conference in modern analysis and pr obability (New Haven, Conn., 1982), Contemp. Math., 1984;26:189–206. https://doi.org/10.1090/conm/026/737400

work page doi:10.1090/conm/026/737400 1982
[30]

Approxima tion with random bases: Pro et contra

Gorban AN, Tyukin I, Prokhorov D, Sofeikov K. Approxima tion with random bases: Pro et contra. Inf. Sci. 2016:364–36 5;129–145. https://doi.org/10.1016/j.ins.2015.09.021

work page doi:10.1016/j.ins.2015.09.021 2016
[31]

Approximate nearest neighbors: tow ards removing the curse of dimensionality

Indyk P , Motwani R. Approximate nearest neighbors: tow ards removing the curse of dimensionality. In STOC’98 Proce edings of the thirtieth annual ACM symposium on Theory of computing, Dallas, Texas, USA – May 24-26, 1998, ACM New Y ork, NY , 1998, pp. 604-613. https://doi.org/10.1145/276698.276876

work page doi:10.1145/276698.276876 1998
[32]

bioRxiv 2017, doi:10.1101/214262

Gao P , Trautmann E, Y u B, Santhanam G, Ryu S, Shenoy K, Ganguli S. A theory of multineuronal dimensionality, dynamicsand measurement, bioRxiv 2017;214262. https://doi.org/10.1101/214262

work page doi:10.1101/214262 2017
[33]

High-dimensional brain

Tyukin IY , Gorban AN, Calvo C, Makarova J, Makarov V A. High-dimensional brain. A tool for encoding and rapid learnin g of memories by single neurons, Bull. Math. Biol. 2018 https://doi.org/10.1007/s11538-018-0415-5

work page doi:10.1007/s11538-018-0415-5 2018
[34]

Large-scale model of mammal ian thalamocortical systems

Izhikevich EM, Edelman GM. Large-scale model of mammal ian thalamocortical systems. Proc. Natl. Acad. Sci. U.S.A. 2008 105(9):3593-8. https://doi.org/10.1073/pnas.0712231105

work page doi:10.1073/pnas.0712231105 2008
[35]

Roberts A, Conte D, Hull M, Merrison-Hort R, al Azad AK, B uhl E, Borisyuk R, Soffe SR. J. Neurosci. 2014 34(2):608-21. https://doi.org/10.1523/JNEUROSCI.3248-13.2014 5

work page doi:10.1523/jneurosci.3248-13.2014 2014

[1] [1]

The unreasonable effectiveness of small neu ral ensembles in high- dimensional brain

K˚ urkov´ a V . Some insights from high-dimensional spheres: Comment on “The unreasonable effectiveness of small neu ral ensembles in high- dimensional brain” by Alexander N. Gorban et al. Phys Life Re v 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.014

work page doi:10.1016/j.plrev.2019.03.014 2019

[2] [2]

The Borsuk-Ulam theorem solves the cu rse of dimensionality: Comment on ”The unreasonable effect ive- ness of small neural ensembles in high-dimensional brain” b y Alexander N

Tozzi A, Peters JF. The Borsuk-Ulam theorem solves the cu rse of dimensionality: Comment on ”The unreasonable effect ive- ness of small neural ensembles in high-dimensional brain” b y Alexander N. Gorban et al. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.04.008

work page doi:10.1016/j.plrev.2019.04.008 2019

[3] [3]

The unreasonable ef- fectiveness of small neural ensembles in high-dimensional brain

V arona P . High and Low dimensionality in Neuroscience an d Artiﬁcial Intelligence: Comment on “The unreasonable ef- fectiveness of small neural ensembles in high-dimensional brain” by A.N. Gorban et al. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.02.008

work page doi:10.1016/j.plrev.2019.02.008 2019

[4] [4]

Brainland

Barrio R. “Brainland” vs. “ﬂatland”: how many dimension s do we need in brain dynamics? Comment on the paper “The unrea son- able effectiveness of small neural ensembles in high-dimen sional brain” by Alexander N. Gorban et al. Phys Life Rev 2019 ; this issue. https://doi.org/10.1016/j.plrev.2019.02.010

work page doi:10.1016/j.plrev.2019.02.010 2019

[5] [5]

The unreasonable effectiveness of small neural ense mbles in high- dimensional brain

Kreiman G. It’s a small dimensional world after all: Comm ent on “The unreasonable effectiveness of small neural ense mbles in high- dimensional brain” by Alexander N. Gorban et al. Phys Life Re v 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.015

work page doi:10.1016/j.plrev.2019.03.015 2019

[6] [6]

The unreasonable effectiveness of small neural ensembles in high-dimension al brain

Fortuna L. Nonlinear effects for the reinforcement of sm all neural ensembles in high dimensional brain: Comment on “ The unreasonable effectiveness of small neural ensembles in high-dimension al brain” by A.N. Gorban, V .A. Makarov, I.Y . Tyukin. Phys Lif e Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.004

work page doi:10.1016/j.plrev.2019.03.004 2019

[7] [7]

The unreasonable effectiveness of small neural ensembles in high-dimensional brain

V an Leeuwen C. The reasonable ineffectiveness of biolog ical brains in applying the principles of high-dimensional cybernetics: Comment on “The unreasonable effectiveness of small neural ensembles in high-dimensional brain” by Alexander N. Gorban et al. Phy s Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.03.005

work page doi:10.1016/j.plrev.2019.03.005 2019

[8] [8]

Akakhievitch revisited: Comment on ”Th e unreasonable effectiveness of small neural ensembles in h igh-dimensional brain” by Alexander N

Quian Quiroga R. Akakhievitch revisited: Comment on ”Th e unreasonable effectiveness of small neural ensembles in h igh-dimensional brain” by Alexander N. Gorban et al. Phys Life Rev 2019; this i ssue. https://doi.org/10.1016/j.plrev.2019.02

work page doi:10.1016/j.plrev.2019.02 2019

[9] [9]

The heresy of unheard-of simplicity: Comm ent on ”The unreasonable effectiveness of small neural en- sembles in high-dimensional brain” by A.N

Kreinovich V . The heresy of unheard-of simplicity: Comm ent on ”The unreasonable effectiveness of small neural en- sembles in high-dimensional brain” by A.N. Gorban, V .A. Mak arov, and I.Y . Tyukin. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2019.04.006

work page doi:10.1016/j.plrev.2019.04.006 2019

[10] [10]

Paris: Gauthier-Villars, 1951

L´ evy P .Probl` emes concrets d’analyse fonctionnelle. Paris: Gauthier-Villars, 1951

work page 1951

[11] [11]

An Elementary Introduction to Modern Convex Geometry

Ball K. An Elementary Introduction to Modern Convex Geometry. Flavors of Geometry, V ol. 31. Cambridge, UK: MSRI Publications; 1997. https://doi.org/10.1007/BF02699376

work page doi:10.1007/bf02699376 1997

[12] [12]

Concentration of measure and isoperimetr ic inequalities in product spaces

Talagrand M. Concentration of measure and isoperimetr ic inequalities in product spaces. Publications Mathematiques de l’IHES 1995;81:73– 205

work page 1995

[13] [13]

Probabilistic Bounds for Binary Classiﬁcation of Large Data Sets

K˚ urkov´ a V , Sanguineti M. Probabilistic Bounds for Binary Classiﬁcation of Large Data Sets. In: Oneto L, Navarin N , Sperduti A, Anguita D. (eds) Recent Advances in Big Data and Deep Learning. INNSBDD L 2019. Proceedings of the International Neural Networks So ciety, vol 1. Springer, pp. 309–319. https://doi.org/10.1007/978-3-030-16841-4_32

work page doi:10.1007/978-3-030-16841-4_32 2019

[14] [14]

Stochastic separation theorems

Gorban AN, Tyukin IY . Stochastic separation theorems. Neural Netw. 2017;94:255–259. https://doi.org/10.1016/j.neunet.2017.07.014

work page doi:10.1016/j.neunet.2017.07.014 2017

[15] [15]

Augmented Artificial Intelligence: a Conceptual Framework

Gorban AN, Grechuk B, Tyukin IY . Augmented Artiﬁcial In telligence: a Conceptual Framework, arXiv preprint 2018, a rXiv:1802.02172 [cs.AI]. https://arxiv.org/abs/1802.02172

work page internal anchor Pith review Pith/arXiv arXiv 2018

[16] [16]

C orrection of AI systems by linear discriminants: Probabili stic foundations

Gorban AN, Golubkov A, Grechuk B, Mirkes EM, Tyukin IY . C orrection of AI systems by linear discriminants: Probabili stic foundations. Inf. Sci. 2018; 466:303-22. https://doi.org/10.1016/j.ins.2018.07.040

work page doi:10.1016/j.ins.2018.07.040 2018

[17] [17]

The unreasonable effe ctiveness of small neural ensembles in high-dimensional br ain

Gorban AN, Makarov V A, Tyukin IY . The unreasonable effe ctiveness of small neural ensembles in high-dimensional br ain. Phys Life Rev 2019; this issue. https://doi.org/10.1016/j.plrev.2018.09.005

work page doi:10.1016/j.plrev.2018.09.005 2019

[18] [18]

Observed universality of phase tran sitions in high-dimensional geometry, with implications f or modern data analysis and signal processing

Donoho D, Tanner J. Observed universality of phase tran sitions in high-dimensional geometry, with implications f or modern data analysis and signal processing. Phil. Trans. R. Soc. A 2009;367:4273 –4293. https://doi.org/10.1098/rsta.2009.0152

work page doi:10.1098/rsta.2009.0152 2009

[19] [19]

Principal manifolds and graphs i n practice: from molecular biology to dynamical systems

Gorban AN, Zinovyev A. Principal manifolds and graphs i n practice: from molecular biology to dynamical systems. In ternational Journal of Neural Systems 2010;20(03):219–232. https://doi.org/10.1142/S0129065710002383

work page doi:10.1142/s0129065710002383 2010

[20] [20]

(eds.) Principal Manifolds for Data Visualisation and Dimension R eduction

Gorban AN, K´ egl B, Wunsch D, Zinovyev A. (eds.) Principal Manifolds for Data Visualisation and Dimension R eduction. Lecture Notes in Computational Science and Engineering, V ol. 58. Berlin – Heidelberg – New Y ork: Springer, 2008. 4

work page 2008

[21] [21]

Data complexity measured by princ ipal graphs

Zinovyev A, Mirkes E. Data complexity measured by princ ipal graphs. Comput. Mat. Appl. 2013;65(10):1471–1482. https://doi.org/10.1016/j.camwa.2012.12.009

work page doi:10.1016/j.camwa.2012.12.009 2013

[22] [22]

Gorban AN, Tyukin IY , Blessing of dimensionality: math ematical foundations of the statistical physics of data, Ph il. Trans. R. Soc. A 2018;376:20170237. https://doi.org/10.1098/rsta.2017.0237

work page doi:10.1098/rsta.2017.0237 2018

[23] [23]

Single-cell trajectori es reconstruction, exploration and mapping of omics data wi th STREAM

Chen H, Albergante L, Hsu JY , Lareau CA, Bosco GL, Guan J, Zhou S, Gorban AN, Bauer DE, Aryee MJ, Langenau DM, Zinovyev A , Buenrostro JD, Y uan G-C, Pinello L. Single-cell trajectori es reconstruction, exploration and mapping of omics data wi th STREAM. Nature Communications 2019;10:1903. https://doi.org/10.1038/s41467-019-09670-4

work page doi:10.1038/s41467-019-09670-4 2019

[24] [24]

Generalization of a theorem of Lusternik-Schni relman on covering of spheres

Fet AI. Generalization of a theorem of Lusternik-Schni relman on covering of spheres. Dokl. Akad. Nauk SSSR 1954;95 :1149-1152

work page 1954

[25] [25]

The multidimensional brain

Tozzi A. The multidimensional brain. Phys Life Rev 2019 . https://doi.org/10.1016/j.plrev.2018.12.004

work page doi:10.1016/j.plrev.2018.12.004 2019

[26] [26]

Estimating the effective dimension of large biological datasets using Fisher separability analysis

Albergante L, Bac J, Zinovyev A. Estimating the effecti ve dimension of large biological datasets using Fisher sepa rability analysis, 2019, arXiv:1901.06328 [cs.LG]. https://arxiv.org/pdf/1901.06328.pdf

work page internal anchor Pith review Pith/arXiv arXiv 2019

[27] [27]

Laboratory of advanced methods for high-dimensional d ata analysis https://github.com/lamhda

work page

[28] [28]

Discrete Sequential Informat ion Coding: Heteroclinic Cognitive Dynamics

Rabinovich MI, V arona P . Discrete Sequential Informat ion Coding: Heteroclinic Cognitive Dynamics. Front Comput Neurosci 2018;12:73. https://doi.org/10.3389/fncom.2018.00073

work page doi:10.3389/fncom.2018.00073 2018

[29] [29]

Extensions of Lipschitz ma ps into a Hilbert space.Conference in modern analysis and pr obability (New Haven, Conn., 1982), Contemp

Johnson W, Lindenstrauss J. Extensions of Lipschitz ma ps into a Hilbert space.Conference in modern analysis and pr obability (New Haven, Conn., 1982), Contemp. Math., 1984;26:189–206. https://doi.org/10.1090/conm/026/737400

work page doi:10.1090/conm/026/737400 1982

[30] [30]

Approxima tion with random bases: Pro et contra

Gorban AN, Tyukin I, Prokhorov D, Sofeikov K. Approxima tion with random bases: Pro et contra. Inf. Sci. 2016:364–36 5;129–145. https://doi.org/10.1016/j.ins.2015.09.021

work page doi:10.1016/j.ins.2015.09.021 2016

[31] [31]

Approximate nearest neighbors: tow ards removing the curse of dimensionality

Indyk P , Motwani R. Approximate nearest neighbors: tow ards removing the curse of dimensionality. In STOC’98 Proce edings of the thirtieth annual ACM symposium on Theory of computing, Dallas, Texas, USA – May 24-26, 1998, ACM New Y ork, NY , 1998, pp. 604-613. https://doi.org/10.1145/276698.276876

work page doi:10.1145/276698.276876 1998

[32] [32]

bioRxiv 2017, doi:10.1101/214262

Gao P , Trautmann E, Y u B, Santhanam G, Ryu S, Shenoy K, Ganguli S. A theory of multineuronal dimensionality, dynamicsand measurement, bioRxiv 2017;214262. https://doi.org/10.1101/214262

work page doi:10.1101/214262 2017

[33] [33]

High-dimensional brain

Tyukin IY , Gorban AN, Calvo C, Makarova J, Makarov V A. High-dimensional brain. A tool for encoding and rapid learnin g of memories by single neurons, Bull. Math. Biol. 2018 https://doi.org/10.1007/s11538-018-0415-5

work page doi:10.1007/s11538-018-0415-5 2018

[34] [34]

Large-scale model of mammal ian thalamocortical systems

Izhikevich EM, Edelman GM. Large-scale model of mammal ian thalamocortical systems. Proc. Natl. Acad. Sci. U.S.A. 2008 105(9):3593-8. https://doi.org/10.1073/pnas.0712231105

work page doi:10.1073/pnas.0712231105 2008

[35] [35]

Roberts A, Conte D, Hull M, Merrison-Hort R, al Azad AK, B uhl E, Borisyuk R, Soffe SR. J. Neurosci. 2014 34(2):608-21. https://doi.org/10.1523/JNEUROSCI.3248-13.2014 5

work page doi:10.1523/jneurosci.3248-13.2014 2014