Hitchikers Guide To Machine Learning

User Manual:

Open the PDF directly: View PDF PDF.
Page Count: 48

HITCHHIKERS GUIDE TO ROCKING MACHINE
LEARNING IN 2019
Session for NewBies
Sho Fola Soboyejo
Apr 26th, 2019
@shoreason
10,000 hours
Photo by: Douglas Adams
PERSONAL APPLICATIONS
Energy utilization anomaly
detection
PERSONAL APPLICATIONS
Recommendation
Engine for nearby fun
activities
PERSONAL APPLICATIONS
Creating clusters and tiers for
fantasy football players plus
predicting performance
PERSONAL APPLICATIONS
Text Summarizer to summarize news articles
80/20 Rule
CHOOSING A PATH
What are you saying No to?
LITERACY
Learning to know
COMPETENCE
VS
Learning to Do
Amazon
ON GETTING STARTED
•Being clear where you are
starting from
•Know where you are
headed before you start
IS THIS YOU?
•Learning a new instrument
•Top Down = Starting with
a song
•Bottom Up = Learn A lot
of Theory
PLAYING THE WHOLE GAME
•David Perkins
•Learning things on
as needed basis
WORK ON THE HARD PARTS
•Zone of discomfort
•Circle of 5ths & Riffs
•Getting and cleaning data
•Setting up your cloud env
•Moving from Python
Notebook to CMD Line
RESOURCES
•Fast.ai - Intro to ML Course
•Udacity ML Course
•Machine Learning is fun -
Medium Blog (Literacy)
•Deep Learning - Online book
(Literacy)
•Follow Siraj Raval, Sentdex and
Corey Schafer on YouTube
LANGUAGES VS TO O L S
@prat0s
Neural Networks & Deep Learning
Machine Learning
PLATFORMS
FINDING A PROJECT AND
DATA
•Kaggle
•UCI ML Repository
•Fast.ai Datasets
•Your own personal project
•Hackathons
RIGHT MIX OF EXPERIENCE
AND MOTIVATION
ACHIEVING SUCCESS
FINDING MOTIVE
•Staying competitive (in your industry)
•Improving your productivity
•Being in the driver’s seat
•Managing Bias
Cranfield University Blogs
FINDING MOTIVE
•Staying competitive (in your
industry)
•Improving your
productivity
•Being in the driver’s seat
•Managing Bias
Cranfield University Blogs
FINDING MOTIVE
•Staying competitive (in your industry)
•Improving your productivity
•Being in the driver’s seat
•Managing Bias
Cranfield University Blogs
“Predictive analytics will have an effect on who
gets hired, is approved for a loan or sees an Ad”
FINDING MOTIVE
•Staying competitive (in your industry)
•Improving your productivity
•Being in the driver’s seat
•Managing Bias
Cranfield University Blogs
The Timeline
Nvidia
Support Vector Machines
Random Forest
Logistic Regression
Linear Regression
K-Nearest Neighbors
K-Means Clustering
Naive Bayes Principal Component Analysis
Linear Discriminant Analysis
Neural Networks
10 Algorithms To Know
“99% OF
THE ECONOMIC
VALUE LIES IN
SUPERVISED
LEARNING”
Photo by: Douglas Adams
AI Fail
VS
Human Fail
ARTIFICIAL INTELLIGENCE
(OR LACK OF IT)
MORE APPLICATIONS
•Product Defect Detection Using Image Recognition
•Customer Interaction Bots
•Fraud, Anomaly and Bad Actor Detection
•Emotion Detection (Mental Health & Counseling)
•Self Driving Cars
Discover Magazine
Literacy
Competency
HANDS-ON
TIME
Black Box: Sci-kit Learn Example
Credit: Adam Geitgey
Support Vector Machines
Great for
classification
problems with
numerical features
and relatively few
samples
Credit: Adedapo Alabi
Initialize: clf = svm.SVC(gamma=0.001, C=100)
Train: clf.fit(x, y)
Test: clf.score(x_test, y_test)
Predict: clf.predict(test)
Key Steps
Scikit Learn Example
Photo by: Douglas Adams
DECEMBER 2019
DECEMBER 2019
@shoreason
www.linkedin.com/in/shofola/
github.com/shoreason

Navigation menu