Lecture 1
Lecture 1
• Recognizing patterns:
– Facial identities or facial expressions
– Handwritten or spoken words
– Medical images
• Generating patterns:
– Generating images or motion sequences (demo)
• Recognizing anomalies:
– Unusual sequences of credit card transactions
– Unusual patterns of sensor readings in a nuclear
power plant or unusual sound in your car engine.
• Prediction:
– Future stock prices or currency exchange rates
Some web-based examples of machine learning
• Example: Credit
scoring
• Differentiating
between low-risk
and high-risk
customers from
their income and
savings
Model
• Example: Price of a
used car
y = wx+w0
• x : car attributes
y : price
y = g (x | θ)
g ( ) model,
θ parameters
21
Unsupervised learning
• Unsupervised learning is a type of machine learning that
looks for previously undetected patterns in a data set with
no pre-existing labels and with a minimum of human
supervision
• The training data set is an unlabeled data set.
• In other words, the training data set contains only the input
value (X) and not the target value (Y).
• Based on the similarity between data, it tries to draw
inference from the data such as finding patterns or clusters
Unsupervised learning Example
Supervised VsUnsupervised learning
Semi-supervised learning
• In this large amount of input data (X) only some of data is labeled.
• It combines datasets of labeled and unlabeled data for training
• Principle of semi-supervised learning is that leveraging a small amount of
labelled data through supervised learning with a larger amount of
unlabeled data through unsupervised learning can yield better accuracy
than completely supervised models in many scenarios Based on the
similarity between data,
• This techniques depend on simulated labeled/unlabeled data by splitting
a fully annotated dataset and is therefore likely to be upper-bounded by
fully supervised learning with all annotations.
Reinforcement learning
• Reinforcement :- Occurrence of an event, in the proper relation to a
response, that tends to increase the probability that the response will
occur again in the same situation.
• Reinforcement Learning:- It is the problem faced by an agent that learns
behaviour through trial and error interaction with dynamic environment.
• It is a learning how to act in order to maximize a numerical reward.
• In this system learns from the feedback provided by environment .
• The feedback is usually in the form of reward or penalty. It is useful to
understand whether a certain action performed in a state is positive or not
• It is a technique to allow an agent to take action and interact with
environment so as to maximize the total rewards
• The sequence of most useful action is a policy that agent has to learn, so
to be able to make best decision in terms of the highest immediate and
cumulative rewards.
• This concept is based on the idea that rational agent always pursues the
objective that can increase his/ her wealth.
• This learning is particularly efficient when environment is not completely
deteminstic.
Reinforcement learning
Reinforcement learning
• Policy:- It is a mapping from perceived states of the environment to
action to be taken when in those states .
• Reward Function:- It defines the goal in reinforcement learning problem.
It maps each perceived state of the environment to a single number,
reward, indicating the intrinsic desirability of the state
• Value Function:- Specifies what is good in the long run. The value of the
state is the total amount of reward an agent can expect to accumulate
over the future, starting from that state
Steps for Reinforcement learning