Upload
chris-orwa
View
524
Download
0
Embed Size (px)
Citation preview
Deep LearningFinding Deep Structures in Data
Chris Orwa3rd March 2016
What is Deep Learning?
“A branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data” - Wikipedia
Tenets of Deep Learning• Multiple Processing Layers• Model data in high abstraction• Learn from abstraction
Our Processing Layers
•Principal Component Analysis• Mantel’s Test• Time Series• Group Theory
Principal Component Analysis • Allow data representation in alternative co-ordinate system. • Provides for dimensionality reduction• Easy to visualize• Emphasize variation in data
Run PCA on Questionnaire
Inconsistency!
Track Changes
Inconsistency!
How can I better capture the changes?
Mantel’s Permutation Test
Mantel’s Test
• Conceived by Nathan Mantel in 1967 • Used to track cancer epidemics• Test correlation between two matrices• Supported in R by APE package
Modify Code
Modify Code Cont’d
What Did I Get?
Same Test on Twitter Data #EastleighBlast
Matrix Representation
Same Test on Forex Data CADUSD,EURGBP, USDJPY
Observations!
There are Two Types of Data• Stable Structure: Does not vary with variation.• Unstable Structure: Varies with variation.
Application!
Scenario I: Stable Structures
Lend Themselves to Two Important Fields
• Spatial Principal Component Analysis
• Group Theory
Library(adegenet)
Scenario II: Unstable Structures
Two Application Areas
•Seasonal Market-Basket Analysis
• Tracking Online Conversations
Sentiment Analysis
Thank You!blackorwa.com
@blackorwa