Presentation is loading. Please wait.

Presentation is loading. Please wait.

CS 425 – F ALL 09 C ORY L EHAN T IM M EYER J ARROD C APPS J ONATHAN B RIDGES F INAL P RESENTATION.

Similar presentations


Presentation on theme: "CS 425 – F ALL 09 C ORY L EHAN T IM M EYER J ARROD C APPS J ONATHAN B RIDGES F INAL P RESENTATION."— Presentation transcript:

1 CS 425 – F ALL 09 C ORY L EHAN T IM M EYER J ARROD C APPS J ONATHAN B RIDGES F INAL P RESENTATION

2 P ROJECT O UTLINE CS 425 - Team Neurotic 2 Cognitive Dissonance Reduction in Neural Networks

3 Participants CS 425 - Team Neurotic 3 Manager Dr. Fujinoki Manager Dr. Fujinoki Client/User Dr. Watson Client/User Dr. Watson Members Tim Meyer Jarrod Capps Jonathan Bridges Members Tim Meyer Jarrod Capps Jonathan Bridges Team Leader Cory Lehan Team Leader Cory Lehan

4 Team Roles CS 425 - Team Neurotic 4 Team Leader Customer Interface Support Cory Lehan Test Manager Process Manager Tim Meyer Implementation Manager Plan Manager Jarrod Capps Design Manager Quality Manager Jonathan Bridges

5 Ethical Considerations CS 425 - Team Neurotic 5 Client Relations  Bi-weekly meetings at client’s discretion. Individual Accomplishments  Author and Co-author tags. Academic Awareness  Put forth best effort, due to the sharing of a group grade.

6 Background Cognitive Dissonance  A cognition can be a belief or attitude a person holds.  Dissonance occurs when cognitions contradict each other.  Very uncomfortable feeling in humans. 6 CS 425 - Team Neurotic Responsibility Cognition 2 Cognition 1 BeliefDissonance Reduction occurs to reduce the unpleasant feeling.

7 Background CS 425 - Team Neurotic 7 Neural Networks  Two main groups: A.I. & Cognitive Modeling. Artificial Intelligence with Neural Networks  Problem solving.  Pattern recognition.  Can be trained or learn. Cognitive Modeling in Neural Networks  Models biological neural systems.  Heavy use of mathematical models.

8 Background CS 425 - Team Neurotic 8 Neural Network for this project  Concerned with modeling, not problem solving.  Based off the Consonance Model from “Connectionist Models of Social Reasoning And Social Behavior”.  Will attempt to simulate dissonance reduction.

9 Background CS 425 - Team Neurotic 9 The Consonance Model.  Cognitions  Two nodes at polar ends.  Resistance to change  Nodes contain an activation level.  Firing rate of neuron.  Represents direction and strength of the attitude or belief (the cognition). + + - - Cognition

10 Background CS 425 - Team Neurotic 10 The Consonance Model.  Cognitions are connected through their nodes bi-directionally.  Connections are weighted positively or negatively.  Cognitions are related positively or negatively. + + - - + + - - Cognition 2Cognition 1

11 R EQUIREMENTS CS 425 - Team Neurotic 11

12 Hardware Environment CS 425 - Team Neurotic 12 What They Are  Windows Environment (XP, Vista, 7)  Minimum disk storage ~50mb  1 GHz Pentium III, or greater, processor. How We Know  Based off requirements of similar software the client runs.

13 Software Requirements CS 425 - Team Neurotic 13 Requirements Gathering  Repeated meetings with the client.  Use Cases  Interface Mock-up to gather features for.

14 Software Requirements CS 425 - Team Neurotic 14 Feature Priority List  Generated from gathering phase.  Priority assigned based off client need, and risk assessment.  Estimates are conservative, and based off previous experience. PriorityItem#Description Est. (days) Very High Neural network components with attributes- 1 Cognitions, Nodes2 2 Connections2 3 Update algorithm for iterations4 4 Neural network creation wizard3 Feature Priority List Example:

15 Software Requirements CS 425 - Team Neurotic 15 Key Features  User created neural network.  Ability to load/save past creations.  Ability to edit properties of a created neural network.  Start/Pause the neural network simulation.  Graphical representation of the neural network.  Graph output of dissonance.

16 D EVELOPMENT E NVIRONMENT CS 425 - Team Neurotic 16

17 Programming Language CS 425 - Team Neurotic 17 What is it?  Java Why?  Helpful Neural Network books with Java.  JFreeChart and JOGL Java libraries.  Java SWING provides interface creation.

18 Libraries CS 425 - Team Neurotic 18 JFreeChart  Allows dynamically created charts.  Meets requirements based off tested code in High-Fidelity prototype. JOGL (Java OpenGL)  Allows the graphical representation of the neural network.  Certain it meets required needs based off previous experience.

19 Software Tools CS 425 - Team Neurotic 19 Subversion  Used with all documents and code. NetBeansIDE  Java support.  JUnit  Subversion support. Doxygen  For generating software reference documentation.

20 Coding & Documentation Standards CS 425 - Team Neurotic 20 Code Comments  Javadoc style comments Indentation  Standard 4 space “hanging paragraph” style. Naming  Camel Casing (e.g. camelCasing)  Noun phrases for class names.  Verb phrases for method names.

21 D EVELOPMENT P LAN CS 425 - Team Neurotic 21

22 Software Engineering Methodology CS 425 - Team Neurotic 22 Based off certain agile “Best Practices”  Customer Involvement  Test Before Code  Code Review and Refactor  Stand-up Meetings  Problem Solving with Patterns

23 Developed in iterations. Gather RequirementsDesign - System StructureIncremental DevelopmentSystem TestingReview & Release Software Process CS 425 - Team Neurotic 23

24 Software Process CS 425 - Team Neurotic 24 Incremental Development  Begins by converting features to tasks. Design Implementation & Unit Testing System Testing Review Feature-to- Task

25 Software Process CS 425 - Team Neurotic 25 Reasons for Process Choice  Adaptability to changing requirements.  Iterative nature gives an early working build.  Allows for a lot of testing.  Keeps client involved through iteration reviews.

26 Risk Analysis CS 425 - Team Neurotic 26 R ISK M ITIGATION T ACTIC Dissonance reduction algorithm doesn’t work. Design pseudo-code of algorithm. Priority of first iteration. Interface and Graph Output don’t interact with one another correctly. Extensive documentation purchased on JFreeChart. Implemented chart in high-fidelity prototype. No working product early enough for client to begin research. The first iteration will contain only the bare and highest-priority items.

27 Project Plan CS 425 - Team Neurotic 27 Iteration #1 – Very High Priority Features

28 Project Plan CS 425 - Team Neurotic 28 Iteration #2 – High Priority Features

29 Project Plan CS 425 - Team Neurotic 29 Iteration #3 – Moderate Priority Features

30 Project Plan CS 425 - Team Neurotic 30 Iteration #4 – Low Priority Features (Optional)

31 Testing Plan CS 425 - Team Neurotic 31 Testing will be done in 3 phases:  Phase 1: Functionality Testing. Done by individual programmer.  Phase 2: Requirements testing. Done by majority of the team including Client.  Phase 3: Final testing of Program. Done by the majority of the team. Unit testing will be done in all Phases.

32 D ESIGN CS 425 - Team Neurotic 32

33 CS 425 - Team Neurotic 33 Static class diagram of system structure Observer Pattern Displays are updated when new data is available. Allows dynamic addition or remove of observing displays. Singleton Pattern Only one instance of the network data can exist. Gives a global access point to the data.

34 Graphics CS 425 - Team Neurotic 34 Displays the Neural Network in a graphical, user-friendly way Takes mouse input for easily modifying the network Tasks are divided into separate classes for expandability

35 Algorithm CS 425 - Team Neurotic 35 Current algorithms are rather simple  Formulas contained in texts Client may need more advanced algorithms  Dynamic connection weights are desired  Both client and team will work together to develop a more advanced algorithm to simulate these changes

36 Algorithm CS 425 - Team Neurotic 36 Pseudo-code created of simple dissonance reduction algorithm, and calculating consonance/dissonance. calculateConsonance { float consonance; for(... Node i) { for(... Connection j) { consonance += Node[i].con[j].weight * Node[i].activation * Node[j].activation; } Sample of calculating consonance:

37 P ROTOTYPE D EMO CS 425 - Team Neurotic 37

38 Questions? CS 425 - Team Neurotic 38 Cory Lehan Tim Meyer Jarrod Capps Jonathan Bridges


Download ppt "CS 425 – F ALL 09 C ORY L EHAN T IM M EYER J ARROD C APPS J ONATHAN B RIDGES F INAL P RESENTATION."

Similar presentations


Ads by Google