Professional Documents
Culture Documents
MACHINE LEARNING
MACHINE LEARNING
Classification Regression
Suppose you have a data set entailing images of
different bikes and cars. Now you need to train
the machine on how to classify all the different
images. How will you create your labelled data?
Classification. Regression:
Height(cms) Age(months)
74 17
The spam filters in an email is an 76 19
example of how classification 78 21
works. 80 23
Unsupervised learning models can be further divided into two
categories:
Refers to the unsupervised learning
algorithm which can cluster the
unknown data according to the
patterns or trends identified out of it.
Clusterin
g
In Natural language Processing, the words are considered to be
N-Dimensional entities. Which means that we cannot visualise
them as they exist beyond our visualisation ability. Hence, to make
sense out of it, we need to reduce their dimensions. Here,
dimensionality reduction algorithm is used.
Dimensionality
Reduction
To reduce the dimensions and still be able to make sense out of the data.
The number of input variables or features for a dataset is
referred to as its Dimensionality.
Large numbers of input features can cause poor performance
for machine learning algorithms.
Dimensionality reduction is a general field of study concerned
with reducing the number of input features.
Let’s play a game:
We have an agent, a robot, and a reward
(diamond here) with many hurdles (fires)
in between.
The goal of the robot is to get the reward
(diamond) and to avoid the hurdles (fire).
The robot learns by trying all the possible
paths and then chooses the path which
reaches the reward while encountering
the least hurdles. Each correct step will
bring the robot closer to the diamond
while accumulating some points and each
wrong step will push the robot away from
the diamond and will take away some of
the accumulated points. The reward
(diamond) will be assigned to the robot
when it reaches the final stage of the Reinforcement
game
Learning
Supervised
Vs
Unsupervised
Vs
Reinforcement Learning
Labeled data set of Only unlabeled input No input/predefined
input and output. is given. It will not add is provided .Its input
Machine already knows labels into the output depends on its action
the output at training also. It will be able to .It collects the data
period .After the classify the data as from the action .Each
training the machine per the patterns or action fetches a
will be fed new dataset characteristics of reward or a demerit.
to predict the result. data.
Reinforcement learning- Robotics-(robot does not know any thing
about its surrounding. Its world depends on its action whether it
chooses to go left or right or forward).
Forecast Discover Learn series of
outcomes underlying
patterns , action
association etc.
Training is well defined. In In unsupervised training There is no
the training phase the there is no labeled data. training data
algorithm is fed with the The algorithm has to given. The whole
proper input whose output identify the trends the reinforcement
/result is known. Hence it is data with out knowing the process
like a trainer supervising result hence training is combines training
the entire thing process. vague. and testing.
Approach is very clear. Algorithm has to find out No data input. It
The algorithm only have the association or trends has to use a trial
to map the know input to in the data and then come and error method
the know output. out with result with out like a child learns
any external help. and adapts to the
world on its own.
used in business for Recommendations on
risk analysis, sales websites, fraud detection,
Self Driving
forecast ,credit clustering movies on the
cars, gaming
analysis, etc basis of the likes on social
media ,market basket
association
Supervised learning
Supervised learning is a type of system in which
both input and desired output data are provided.
The term supervised learning comes from the idea
that an algorithm is learning from a training
dataset, which can be thought of as the teacher.
Supervised machine learning systems provide the
learning algorithms with known quantities to
support future judgments.
Applications of supervised learning are typically
broken down into two categories, classification
and regression.
Unsupervised Learning