Introduction to Computational Cognition Course
Spring, 2012
Prof. Larry Manevitz, Instructor
EXAMINATION
MOED A GUIDELINES
Here are sample questions for MOED A. The questions may differ in form; some may
be “American”; some may be
open ended. However, the information
you will need to reply is the same as for these questions.
The exam will be closed (i.e. no
help pages).
1)
You have to know the following networks
i) Hopfield Network
ii) SDM
iii)
EE and FM Human Declarative Memory
iv) Kohonen
Network
2) You will need to know the
abilities and differences between:
i) Perceptron
(McCullough-Pitts Neuron)
ii) Network of such neurons
iii) Liquid Integrate and Fire (LIF)
neurons
3)
You need to know well what are the following methods
for machine learning:
i) one
–class learning
ii) two class learning 3)
You need to know how Kohonen algorithm works
4) You need to know how feed forward
neural networks work
5)
You need to know the following model
neurons: i)
McCullough-Pitts ii) Sigmoid iii) Leaky
Integrate and Fire Neuron
6) Know that one McCullough Pitts
Neuron can only classify linearly separated sets neurons while a network can in
principle separate arbitrary classifications
Sample Questions (exam questions will require the same knowledge as these but may be expressed differently):
Questions for Course on Computational Cognition
1. Explain why fMRI scans can be used to identify cognitive states. What classifying systems can be used?
2. Why should feature selection be useful?
3. Describe the difference between one-class and two class classification.
4. Describe the system used for one-class classification of fMRI from the Boehm-Hardoon-Manevitz paper?
5. Describe and compare the SDM and the Hopfield associative memory systems
6. What is an “attractor”?
7. How is a memory associated with an “attractor” in a Hopfield network.
8. What purpose does the hamming distance serve in SDM.
9. Describe how a Kohonen map could result in a somatosensory mapping. Make sure you describe the function of the topology.
10. What is meant by “equiprobable topological map” in the context of Kohonen mapping.
11. Describe the set up of the “Liquid State Machine”.
12. According to the paper by Hananel Hazan, what is the importance of "topologies" on the liquid?. What is the result of using, e.g. a "small world" topology.
13. Describe how “randomness” is used in (i) SDM (ii) Liquid State Machines
14. Describe the set up in NET Talk. What does the network look like? How is the information placed in the network.
15. Describe the capabilities and limitations of
(i) Perceptron (ii) Network of McCullough Pitts neurons (iii) Liquid Integrate and Fire neuron
16. 1) What is a somatosensory map? Explain how this might be formed by a Kohonen algorithm.
17)
i) what is the
difference in the human declarative memory system EE and FM
ii) explain
how machine learning could help establish their separate existence from fMRI
signals
18)
Describe and compare Hopfield Associative Memory with Sparse Distributed
Memory.
Below are materials from the course (Some may be repeated more than once and you are not responsible for all the material here.)
You can also look in Wikipedia or in a standard Neural Network Book (Such as Faussett, Introduction to Neural Networks) for background on the computational neural networks.
0.Students Notes (accuracy not guaranteed)
2.Background in Kinds of Neurons and Networks
3. NetTalk and Feedforward net
5.Reading the Mind, one class and feature representation
7. Sparse Distributed Memory Associative Memory and TSDM
9. Kohonen Algorithm and Self Organizing Maps
12. Disambiguifying in Silent Reading
This site is under construction
1. Here are slides from the first lecture
2. Here are the slides of the general overview of “Classical Neural Networks”
NetTalk Original Paper
NetTalk Data Set
Interview with Mitchell and Just
Hardoon-Manevitz-Boehm Lecture on One Class Reading the Brain
For Work on Hopfield Associative Memory Consult any text on Neural Networks
Temporal Sparse Distributed Memory
Talk on Using fMRI to discover alternative declarative associative memory