5. 1943 1950 1956 1968 1969 1973 1981 1990 1997
AI KEYNOTES THROUGHOUT TIME
2002 2005 2008 2010 2011 2014
WW2
Robot
Story
Top-Down
Approach
2001: A Space
Odyssey
Shakey the
Robot
The AI
Winter
A solution for
big business
Back to
Bottom-up
Man vs
machine
Roomba
War
Machines
Google’s Speech
Recognition
Dance Bots
Man vs machine
21st century
Are machine
intelligent now?
15. def checkColor(img):
#lots of code
def checkSize(img):
#lots of code
def checkTexture(img):
#lots of code
def analyzeShape(img):
#lots of code
MACHINE LEARNING WITH PYTHON | AUG 2017
16. ● Develop systems that can automatically adapt and
customize themselves to individual users.
● Discover new knowledge from large databases (data
mining)
● Ability to mimic human and replace certain
monotonous tasks which require some intelligence.
● Develop systems that are too difficult/expensive to
construct manually because they require specific and
detailed skills or knowledge tuned to a specific task.
MACHINE LEARNING WITH PYTHON | AUG 2017
21. ● Supervised Learning
● Unsupervised Learning
● Reinforcement Learning
MACHINE LEARNING WITH PYTHON | AUG 2017
22. consist of a target / outcome variable (or dependent
variable) which is to be predicted from a given set of
predictors (independent variables). Using these set of
variables, we generate a function that map inputs to
desired outputs. The training process continues until
the model achieves a desired level of accuracy on
the training data.
SUPERVISED LEARNING
MACHINE LEARNING WITH PYTHON | AUG 2017
23. Create a classifier by finding
patterns in examples.
SUPERVISED LEARNING
MACHINE LEARNING WITH PYTHON | AUG 2017
TRAIN
CLASSIFIER
MAKE
PREDICTION
COLLECT
TRAINING
DATA
25. do not have any target or outcome variable to
predict / estimate. It is used for clustering
population in different groups, which is widely used
for segmenting customers in different groups for
specific intervention.
UNSUPERVISED LEARNING
MACHINE LEARNING WITH PYTHON | AUG 2017