Attended a meetup on AI and Machine learning conducted by Harinder.
https://www.meetup.com/All-About-Design-Patterns/events/248506302/
Short notes on same:
AI -> artificially created intelligence
Machine learning is an *important* approach to AI. (There are many approaches out there).
--
Some applications:
Why Candy crush was so famous ?
According to the player's habits, the game adjusts itself to ensure that the player stays for long.
Facebook, Google maps etc., makes use of AI.
recaptcha -> use this to crowsource old book's scanning.
youtube suggestions
Spam detection
Deep learning
Natural language processing.
---
John Mccarthy coined the term AI. 1959.
https://en.wikipedia.org/wiki/John_McCarthy_(computer_scientist)
many developments followed especially games played by AI.
1997 -> Deepblue played chess
2005 -> self driving car
2011 -> watson jeopardy
2016 -> alphago game
Don't take games lightly :)
----------
2005 -> 135 Exabyte human data
Now -> 100,000 exabytes !!
(1 Exabyte -> 1000 PB -> 1PB=1000 TB -> 1TB=1000 GB)
So much of DATA and so much of computing power, hence good interest now.
------------
Given x and y whose values are linear , AI can figure out
y = mx+c
// slope and interceptor
Here, y=mx+c is the model figured out by AI.
It can use the model to get output for any input.
what if scatter plot ?
make use of squares to get smaller numbers.
Fit the DATA -> important term
Fit the DATA to figure out the MODEL.
machine learning -> supervised
-> unsupervised
supervised -> regression
-> classification
supervised -> labelled.
unsupervised -> unlabeled.
Regression -> continuous output
classification -> well defined classes
Machine learning:
1. Fit
data -> learning -> model
eg: model -> y = mx+c
2. Predict
testdata -> model -> New value (prediction)
So, out of 30 test data
Use 20 test data get the model.
compare with actual output.
helps to know whether algorithm is good / bad.
model -> forumla / rules.
test data =================
-> test data accuracy
actual output -----------------------
train data =================
-> train data accuracy
actual output -----------------------
(test data is part of train data)
Avoid over fitting (100% data accuracy).
(Remembered) data
4 important points in ML:
1. good data - data needs to be cleaned.
2. Algorithm
3. Features.
4. Parameter tuning.
AI framework :
https://www.anaconda.com/download
Machine learning in python:
http://scikit-learn.org/stable/
