I AM Pratik Parmar
Hello!
And I am here to bore you with Machine Learning.
Slide 3
Slide 3 text
Machine Learning for everyone
Slide 4
Slide 4 text
“ Machine Learning is using many
examples to answer questions
Slide 5
Slide 5 text
No content
Slide 6
Slide 6 text
No content
Slide 7
Slide 7 text
?
Machine learning is awesome, except
when it forces you to do advanced
math. Isn’t it?
Slide 8
Slide 8 text
Tensorflow Estimators
Slide 9
Slide 9 text
Tensorflow Estimator
Slide 10
Slide 10 text
App Idea: Food Search engine
0
And foodies be like...
Slide 11
Slide 11 text
Version 2.0
Memorize all the things
Slide 12
Slide 12 text
Version 3.0
More generalized recommendations for all
Slide 13
Slide 13 text
No good deeds goes unpunished
Slide 14
Slide 14 text
Wide and Deep
Memorization
Relevance
Generalization
Diversity
Slide 15
Slide 15 text
Wide and Deep model
Slide 16
Slide 16 text
After evaluation
The workflow for building machine learning
models often ends at the evaluation stage:
you have achieved an acceptable accuracy,
and “ta-da! Mission Accomplished.”
Slide 17
Slide 17 text
Why ???
Maybe, going the extra mile to put your model into
production is not always needed. And even when it
is, this task is delegated to a system administrator.
Slide 18
Slide 18 text
“
During my course at Coursera I was
always asking myself — I have my
model, which I can run in Jupyter
Notebook and see the result, but what
can I do with it? How can other use it?