[Illinois] MCB 493 Lecture 9: Probability Estimation and Supervised Learning

By Thomas J. Anastasio

University of Illinois at Urbana-Champaign

Published on

Abstract

Supervised learning algorithms can train neural units and networks to estimate probabilities and simulate the responses of neurons to multisensory stimulation

9.1 Implementing a Simple Classifier as a Three-Layered Neural Network

9.2 Predicting Rain as an Everyday Example of Probabilistic Inference

9.3 Implementing a Simple Classifier Using Bayes' Rule

9.4 Modeling Neural Responses to Sensory Input as a Probabilistic Inference

9.5 Modeling Multisensory Collicular Neurons as Probability Estimators

9.9.Simulating the Development of Non-Uniform Distributed Representations

9.7 Modeling Non-Uniform Distributed Representations in the Vestibular Nuclei

Cite this work

Researchers should cite this work as follows:

  • Thomas J. Anastasio (2013), "[Illinois] MCB 493 Lecture 9: Probability Estimation and Supervised Learning," https://nanohub.org/resources/18834.

    BibTex | EndNote

Time

Location

University of Illinois at Urbana-Champaign, Urbana, IL

Submitter

NanoBio Node

University of Illinois at Urbana-Champaign

Tags

[Illinois] MCB 493 Lecture 9: Chapter 9
  • MCB 493 Lecture 8: Information Transmission and Unsupervised Learning 1. MCB 493 Lecture 8: Information… 0
    00:00/00:00
  • Figure 8.1 Two-input/two-output, feedforward network 2. Figure 8.1 Two-input/two-outpu… 660.05105438401779
    00:00/00:00
  • Table 8.1 (Part 1) 3. Table 8.1 (Part 1) 1789.184251465954
    00:00/00:00
  • Table 8.1 (Part 2) 4. Table 8.1 (Part 2) 1893.4601052872511
    00:00/00:00
  • Table 8.1 (Part 3) 5. Table 8.1 (Part 3) 2002.27087815671
    00:00/00:00
  • Table 8.2 (Part 1) 6. Table 8.2 (Part 1) 2299.7831082627604
    00:00/00:00
  • Table 8.2 (Part 2) 7. Table 8.2 (Part 2) 2533.2225421637186
    00:00/00:00
  • Table 8.3 8. Table 8.3 3072.6948185345814
    00:00/00:00
  • Figure 8.2 Blind source separation using the Bell–Sejnowski information maximization algorithm 9. Figure 8.2 Blind source separa… 3206.5548051683277
    00:00/00:00
  • Figure 8.3 Learning a sparse code for natural images 10. Figure 8.3 Learning a sparse c… 3340.3092475317626
    00:00/00:00
  • Figure 8.4 The receptive fields of neurons in primary visual cortex are well described using two-dimensional Gabor functions 11. Figure 8.4 The receptive field… 3379.5538190068064
    00:00/00:00
  • Figure 8.5 Percentages of neurons in the deep layers of the superior colliculus having each of seven different selectivities for stimulus modality 12. Figure 8.5 Percentages of neur… 3469.577865379656
    00:00/00:00
  • Figure 8.6 Information extraction and percentages of multisensory units in a superior colliculus model 13. Figure 8.6 Information extract… 3510.4934962835905
    00:00/00:00
  • Table 8.4 14. Table 8.4 3788.9855955678668
    00:00/00:00
  • Figure 8.7 The one-dimensional self-organizing map (SOM) model of the superior colliculus 15. Figure 8.7 The one-dimensional… 3956.4184210526319
    00:00/00:00
  • Figure B8.2.1 A typical rate-distortion curve 16. Figure B8.2.1 A typical rate-d… 4218.5888724070537
    00:00/00:00
  • Table 8.5 (Part 1) 17. Table 8.5 (Part 1) 4266.332705275684
    00:00/00:00
  • Table 8.5 (Part 2) 18. Table 8.5 (Part 2) 4553.4269700332961
    00:00/00:00
  • Figure 8.8 Overcoming the deleterious effects of input background activity on information transmission in the one-dimensional SOM model of the superior colliculus 19. Figure 8.8 Overcoming the dele… 4792.6636882205112
    00:00/00:00
  • Figure 8.8 Overcoming the deleterious effects of input background activity on information transmission in the one-dimensional SOM model of the superior colliculus (Part 1) 20. Figure 8.8 Overcoming the dele… 4958.181457110677
    00:00/00:00
  • Figure 8.8 Overcoming the deleterious effects of input background activity on information transmission in the one-dimensional SOM model of the superior colliculus (Part 2) 21. Figure 8.8 Overcoming the dele… 5007.0421473981633
    00:00/00:00