What we learn from the learning rate

被引:14
|
作者
Brittain, Rory A. [1 ]
Jones, Nick S. [1 ]
Ouldridge, Thomas E. [2 ]
机构
[1] Imperial Coll London, Dept Math, London SW7 2AZ, England
[2] Imperial Coll London, Dept Bioengn, London SW7 2AZ, England
关键词
information processing; signal transduction; statistical Inference in biological systems; stochastic processes; IRREVERSIBILITY; THERMODYNAMICS;
D O I
10.1088/1742-5468/aa71d4
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
The learning rate is an information-theoretical quantity for bipartite Markov chains describing two coupled subsystems. It is defined as the rate at which transitions in the downstream subsystem tend to increase the mutual information between the two subsystems, and is bounded by the dissipation arising from these transitions. Its physical interpretation, however, is unclear, although it has been used as a metric for the sensing performance of the downstream subsystem. In this paper, we explore the behaviour of the learning rate for a number of simple model systems, establishing when and how its behaviour is distinct from the instantaneous mutual information between subsystems. In the simplest case, the two are almost equivalent. In more complex steady-state systems, the mutual information and the learning rate behave qualitatively distinctly, with the learning rate clearly now reflecting the rate at which the downstream system must update its information in response to changes in the upstream system. It is not clear whether this quantity is the most natural measure for sensor performance, and, indeed, we provide an example in which optimising the learning rate over a region of parameter space of the downstream system yields an apparently sub-optimal sensor.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] WHAT WE CAN LEARN FROM INVERTEBRATE LEARNING
    KRASNE, FB
    GLANZMAN, DL
    [J]. ANNUAL REVIEW OF PSYCHOLOGY, 1995, 46 : 585 - 624
  • [2] WHAT CAN WE LEARN FROM THE EFFECTIVE RATE OF PROTECTION
    HARTIGAN, JC
    [J]. WELTWIRTSCHAFTLICHES ARCHIV-REVIEW OF WORLD ECONOMICS, 1985, 121 (01): : 53 - 60
  • [3] What do we learn from disciplined practice learning?
    Sheikh, K
    [J]. JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 1996, 276 (06): : 447 - 447
  • [4] Learning From What We Do, and Doing What We Learn: A Learning Health Care System in Action
    Lindsell, Christopher J.
    Gatto, Cheryl L.
    Dear, Mary Lynn
    Buie, Reagan
    Rice, Todd W.
    Pulley, Jill M.
    Hartert, Tina V.
    Kripalani, Sunil
    Harrell, Frank E.
    Byrne, Daniel W.
    Edgeworth, Mitchell C.
    Steaban, Robin
    Dittus, Robert S.
    Bernard, Gordon R.
    [J]. ACADEMIC MEDICINE, 2021, 96 (09) : 1291 - 1299
  • [5] What Are We Learning and What Can We Learn from the Human Oral Microbiome Project?
    Cross B.
    Faustoferri R.C.
    Quivey R.G., Jr.
    [J]. Current Oral Health Reports, 2016, 3 (1) : 56 - 63
  • [6] What did we learn and what will we learn from hydrodynamics at RHIC?
    Kolb, PF
    [J]. INTERSECTIONS OF PARTICLE AND NUCLEAR PHYSICS, 2003, 698 : 694 - 697
  • [7] What Can We Learn About Navigation From Associative Learning?
    McGregor, Anthony
    [J]. COMPARATIVE COGNITION & BEHAVIOR REVIEWS, 2020, 15 : 163 - 186
  • [8] What we learn from extremophiles
    Schroeder, Carola
    Burkhardt, Christin
    Antranikian, Garabed
    [J]. CHEMTEXTS, 2020, 6 (01)
  • [9] What do we learn from this?
    Minne-Kolumne, Helmut W.
    [J]. OSTEOLOGIE, 2014, 23 (03) : 232 - 232
  • [10] What can we learn from it?
    Bogaerts, A
    Gijbels, R
    [J]. ANALYTICAL CHEMISTRY, 1997, 69 (23) : A719 - A727