[Illinois] MCB 493 Lecture 6: Supervised Learning and Non-Uniform Representations

By Thomas J. Anastasio

Department of Molecular and Integrative Physiology , University of Illinois at Urbana-Champaign, Urbana, IL

Published on

Abstract

Supervised learning algorithms can train neural networks to associate patterns and simulate the non-uniform distributed representations found in many brain regions.

6.1 Using the Classic Hebb Rule to Learn a Simple Labeled Line Response

6.2 Learning a Simple Contingency Using the Covariation Rule

6.3 Using the Delta Rule to Learn a Complex Contingency

6.4 Learning Interneuronal Representations using Back-Propagation

6.5 Simulating Catastrophic Retroactive Interference in Learning

6.6 Simulating the Development of Non-Uniform Distributed Representations

6.7 Modeling Non-Uniform Distributed Representations in the Vestibular Nuclei

Bio

THOMAS J. ANASTASIO SYSTEMS NEUROBIOLOGIST I am an associate professor in the University of Illinois Department of Molecular and Integrative Physiology and a full-time faculty member of the Beckman Institute. My main research interest is in Systems Neurobiology, which I define as the application of conceptual and computational methods to complex and multilevel problems in neurobiology. I am also involved in teaching, writing, and technology transfer.

Cite this work

Researchers should cite this work as follows:

  • Thomas J. Anastasio (2013), "[Illinois] MCB 493 Lecture 6: Supervised Learning and Non-Uniform Representations," https://nanohub.org/resources/17022.

    BibTex | EndNote

Time

Location

University of Illinois at Urbana-Champaign, Urbana, IL

Submitter

NanoBio Node, Obaid Sarvana, George Daley

University of Illinois at Urbana-Champaign

Tags

[Illinois] MCB 493 Lecture 6: Chapter 6
  • Lecture 6: Supervised Learning and Non-Uniform Representations 1. Lecture 6: Supervised Learning… 0
    00:00/00:00
  • Figure 6.1 A generic, two-layered feedforward neural network 2. Figure 6.1 A generic, two-laye… 408.55967413441954
    00:00/00:00
  • Table 6.1 3. Table 6.1 592.43772030212858
    00:00/00:00
  • Table 6.2 4. Table 6.2 723.57047379262985
    00:00/00:00
  • Table 6.3 5. Table 6.3 940.7382009613184
    00:00/00:00
  • Table 6.4 6. Table 6.4 1034.9457541771571
    00:00/00:00
  • Table 6.5 7. Table 6.5 1063.698374914168
    00:00/00:00
  • Table 6.6 8. Table 6.6 1127.5187914854657
    00:00/00:00
  • Table 6.7 9. Table 6.7 1163.3295490959031
    00:00/00:00
  • Table 6.8 10. Table 6.8 1208.2787365529871
    00:00/00:00
  • Figure 6.2 Gradient descent in a neural network with only two weights: w1 and w2 11. Figure 6.2 Gradient descent in… 1600.7854428931105
    00:00/00:00
  • Figure 6.3 The squashing function (A) and its derivative (B) over the range −5 to +5 12. Figure 6.3 The squashing funct… 2028.4342412451363
    00:00/00:00
  • Table 6.9 13. Table 6.9 2113.6519569695583
    00:00/00:00
  • Table 6.10 14. Table 6.10 2562.8200539347881
    00:00/00:00
  • Table 6.11 15. Table 6.11 2684.6283480593979
    00:00/00:00
  • Table 6.12 16. Table 6.12 2831.5741481583664
    00:00/00:00
  • Figure 6.4 A generic, three-layered feedforward neural network 17. Figure 6.4 A generic, three-la… 2869.0762174092979
    00:00/00:00
  • Table 6.13 18. Table 6.13 3621.7995337995339
    00:00/00:00
  • Table 6.14 19. Table 6.14 3718.2938159879336
    00:00/00:00
  • Figure 6.5 Demonstrating catastrophic interference 20. Figure 6.5 Demonstrating catas… 3920.238016528926
    00:00/00:00
  • Table 6.15 21. Table 6.15 4200.6902263037064
    00:00/00:00
  • Table 6.16 22. Table 6.16 4275.9399698340876
    00:00/00:00
  • Figure 6.6 Simulating a non-uniform distributed representation 23. Figure 6.6 Simulating a non-un… 4307.1255450431927
    00:00/00:00
  • Figure 6.7 Schematic diagram of the vestibulo-oculomotor system 24. Figure 6.7 Schematic diagram o… 4373.237993138936
    00:00/00:00
  • Figure 6.8 Vestibulo-oculomotor related behavior of vestibular nucleus neurons 25. Figure 6.8 Vestibulo-oculomoto… 4493.4831639641934
    00:00/00:00
  • Table 6.17 26. Table 6.17 4591.9090183824756
    00:00/00:00
  • Figure 6.9 Simulating the non-uniform distributed representation of vestibular and pursuit commands in the vestibular nuclei 27. Figure 6.9 Simulating the non-… 4627.1768105472283
    00:00/00:00
  • Figure 6.10 Simulating the non-uniform distributed representation of sensorimotor activation vectors in the vestibular nuclei 28. Figure 6.10 Simulating the non… 4771.9123070325895
    00:00/00:00
  • Figure 6.11 The non-uniform distributed representation of sensorimotor activation vectors in the real vestibular nuclei 29. Figure 6.11 The non-uniform di… 4803.2309176672379
    00:00/00:00