NeuralNet_report

pdf

School

Georgia Institute Of Technology *

*We aren’t endorsed by this school

Course

3600

Subject

Computer Science

Date

Feb 20, 2024

Type

pdf

Pages

Uploaded by rpeddi7

Neural Net Report Your Name: Rima Peddi Your GT Username: rpeddi7

Question 5: Learning With Restarts 1. testPenData : • Max accuracy: 0.9088050314465409 • Average accuracy: 0.9021726700971984 • Standard deviation: 0.008331555602614543 2. testCarData : • Max accuracy: 0.995 • Average accuracy: 0.9860000000000001 • Standard deviation: 0.0058309518948453055

Question 6: Varying the Hidden Layers Statistic table for testPenData – report the max, average, and standard deviation at various amount of perceptrons. Number of Perceptrons at the Hidden Layer 0 5 10 15 20 25 30 35 40 Max Accuracy 0.0000 0.8496 0.8948 0.9094 0.9085 0.9088 0.9077 0.9062 0.9028 Avg Accuracy 0.0000 0.8400 0.8890 0.9012 0.8979 0.9010 0.9056 0.8986 0.8990 Standard Deviation 0.0000 0.0116 0.0058 0.0076 0.0083 0.0059 0.0012 0.0081 0.0043

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Question 6: Varying the Hidden Layers Create a learning curve for testPenData where the number of hidden layer perceptrons is the independent variable and the average accuracy is the dependent variable.

Question 6: Varying the Hidden Layers For testPenData , discuss any notable trends you saw related to increasing the size of the hidden layers in your neural net. Answer: As the size of the hidden layers increase, the average accuracy increases and then plateaus. There is not a very clear trend, but the data generally increases and plateaus around 15 hidden layers.

Question 6: Varying the Hidden Layers Statistic table for testCarData – report the max, average, and standard deviation at various amount of perceptrons. Number of Perceptrons at the Hidden Layer 0 5 10 15 20 25 30 35 40 Max Accuracy 0.6400 0.9800 0.9700 0.9550 0.9650 0.9700 0.9800 0.9800 0.9800 Avg Accuracy 0.6400 0.9690 0.9640 0.9530 0.9590 0.9610 0.9670 0.9680 0.9610 Standard Deviation 0.0000 0.0086 0.0037 0.0024 0.0037 0.0066 0.0108 0.0081 0.0128

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Question 6: Varying the Hidden Layers Create a learning curve for testCarData where the number of hidden layer perceptrons is the independent variable and the average accuracy is the dependent variable.

Question 6: Varying the Hidden Layers For testCarData , discuss any notable trends you saw related to increasing the size of the hidden layers in your neural net. Answer: As the size of the hidden layers increase, the average accuracy increases sharply and then levels out. The learning curve is not consistent and does not showcase a specific relationship with the number of hidden layers.

Question 7 (extra credit): Learning XOR Report the max accuracy, average accuracy, and standard deviation of the neural net that you have trained with 1) no hidden layer, and 2) a hidden layer with various amount of perceptrons (at least 3 different amounts) No Hidden Layer Hidden Layer ___ perceptrons ___ perceptrons ___ perceptrons Max Accuracy Avg Accuracy Standard Deviation

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Question 7 (extra credit): Learning XOR Report the behavior of the trained neural net without a hidden layer . Answer:

Question 7 (extra credit): Learning XOR Report the behavior of the trained neural net with a hidden layer . Are the results what you expected? Explain your observation. Answer:

Question 8 (extra credit): Novel Dataset List the name and the source of the dataset that you’ve chosen. • Name: ______ • Source (e.g., URLs): ______ • Briefly describe the dataset: _____

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Question 8 (extra credit): Run Stats • Max accuracy: _______ • Average accuracy: _______ • Standard deviation: ________

Question 8 (extra credit): Novel Dataset Describe how to run the code that you’ve set up to train the selected dataset. Answer:

Related Documents

seeing the standards.docx

standard three.docx

Tch 505 Culminating Project 5-30-22.docx

sp21final.pdf

Quiz 1.docx

IST 7040 Week 1 Discussion.docx

Homework 1.pdf

Tutorial01_Case4_Rubric.docx

CS 2203 Programming 1 (5).docx

sample_midterm cs mcq.pdf

fire prevention essay.docx

Course Hero Logo.docx

Recommended textbooks for you

Principles of Information Systems (MindTap Course...

Computer Science

ISBN:9781285867168

Author:Ralph Stair, George Reynolds

Publisher:Cengage Learning

EBK JAVA PROGRAMMING

Computer Science

ISBN:9781337671385

Author:FARRELL

Publisher:CENGAGE LEARNING - CONSIGNMENT

Fundamentals of Information Systems

Computer Science

ISBN:9781337097536

Author:Ralph Stair, George Reynolds

Publisher:Cengage Learning

Principles of Information Systems (MindTap Course...

Computer Science

ISBN:9781305971776

Author:Ralph Stair, George Reynolds

Publisher:Cengage Learning

MIS

Computer Science

ISBN:9781337681919

Author:BIDGOLI

Publisher:Cengage

Systems Architecture

Computer Science

ISBN:9781305080195

Author:Stephen D. Burd

Publisher:Cengage Learning

SEE MORE TEXTBOOKS

Recommended textbooks for you

Principles of Information Systems (MindTap Course...
Computer Science
ISBN:9781285867168
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
EBK JAVA PROGRAMMING
Computer Science
ISBN:9781337671385
Author:FARRELL
Publisher:CENGAGE LEARNING - CONSIGNMENT
Fundamentals of Information Systems
Computer Science
ISBN:9781337097536
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
Principles of Information Systems (MindTap Course...
Computer Science
ISBN:9781305971776
Author:Ralph Stair, George Reynolds
Publisher:Cengage Learning
MIS
Computer Science
ISBN:9781337681919
Author:BIDGOLI
Publisher:Cengage
Systems Architecture
Computer Science
ISBN:9781305080195
Author:Stephen D. Burd
Publisher:Cengage Learning