Machine Learning

BCS303
Machine Learning
Introduction
• Machine learning is a branch of AI concerns
with the construction and study of systems that
can learn from data.
• In 1956, Arthur Samuel defined machine
learning as a field of study that gives computers
the ability to learn without being explicitly
programmed.
• The goal of machine learning is to build
computer systems that can adapt and learn
from their experience (Tom Dietterich).
Introduction
• Tom M. Mitchell provided a widely quoted,
more formal definition: A computer program is
said to learn from experience E with respect to
some class of tasks T and performance
measure P, if its performance at tasks in T, as
measured by P, improves with experience E.
Introduction
• Therefore, Machine learning is about
automating automation, getting computers to
program themselves, writing software is the
bottleneck let the data do the work instead.
• In machine learning computer a provided with
data and output to produce a program while in
traditional programming computer are provided
with data and program to produce output.
Importance of machine learning
• Some tasks cannot be defined well, except by
examples.
• Relationships and correlations can be hidden
within large amounts of data.
• Machine learning / data mining may be able to
find these relationships.
• Human designers often produce machines that
do not work as well as desired in the
environments in which they are used.
Importance of machine learning
• The amount of knowledge available about
certain tasks might be too large for explicit
encoding by humans (e.g. medical diagnostic).
• Environments change over time.
• New knowledge about tasks is constantly
being discovered by humans.
• It may be difficult to continuously re-design
systems by hand.
Generalization
• The core objective of a learner is to generalize
from its experience.
• Generalization in this context is the ability of a
learning machine to perform accurately on new,
unseen examples/ tasks after having
experienced a learning data set.
• A table below provides a comparison between
machine learning and data mining.
Machine learning Data mining
Focuses on prediction, Focuses on the discovery of
based on known properties (previously) unknown
learning from training data properties on the data
Performance is usually The key task is the

evaluated with respect to the discovery of previously
ability to reproduce known unknown knowledge.
knowledge Evaluated with respect to
known knowledge
This is the algorithm part of Application of algorithm to
the data mining process search for patterns and
relationships that may exist
in large databases
Machine learning algorithms
• Machine learning algorithms can be organized
based on the desired outcome of the algorithm
or the type of input available during training the
machine:
• Supervised learning
• Unsupervised learning
• Semi-supervised learning
• Reinforcement learning
Supervised learning
• Algorithms are trained on labeled examples.
• That is, input where the desired output is
known.
• Categories of supervised learning include:
classification (categorical data) and regression
(continuous data whose pair has relationship).
• It is applied in risk assessment, image
classification, fraud detection and visual
recognition.
Unsupervised learning
• Algorithms operate on unlabeled examples.
• That is, input where the desired output is
unknown.
• Grouped in to clustering and association.
• Clustering group things based on their
similarities while association discover the
probability of the co-occurrence of items in a
collection.
Unsupervised learning
• Example of association is when identifying
items that are bough together.
• Unsupervised learning is applied in market
basket analysis, semantic clustering, delivery
store optimization and identifying accident
prone areas.
Semi-supervised and Reinforcement
learning
• Semi-supervised learning combines both
labelled and unlabeled examples to generate
an appropriate function or classifier
• Reinforcement learning concerned with how
intelligent agent ought to act in an environment
to maximize some notion of reward from
sequence of actions.
Decision tree learning
• Uses a decision tree as a predictive model
which maps observations about an item to
conclusions about the item’s target value.
• To classify a new instance, we start at the root
and traverse the tree to reach a leaf.
• At an internal node we evaluate the predicate
(or function) on the data instance to find child to
go.
• The process continues till we reach a leaf node.
Decision tree learning
• We can use greedy algorithm to build a
decision tree.
• Other learning techniques in AI include:
• Artificial neural networks;
• inductive logic programming;
• support vector machines;
• Bayesian networks;
• Reinforcement learning;
• Association Rule Learning and
• Clustering.
Application of Machine Learning
• Machine learning is applied in different
application areas including:
• machine perception,
• object recognition,
• syntactic pattern recognition,
• medical diagnosis,
• brain-machine interfaces,
• detecting credit card fraud,
• classifying DNA sequences,
• Speech and handwriting recognition,
• Software engineering,
• Robot locomotion,
• Computational finance,
• Opinion mining,
• Information retrieval,
• Computer vision,
• Natural language processing,
• Search engines,
• bioinformatics, • structural health
• cheminformatics, monitoring,
• stock market analysis, • affective computing

and
• sequence mining,
• recommender
• game playing, systems.
• adaptive websites,
• computational
advertising,
Machine Learning Software
• Software suites • MATLAB mlpy,
containing a variety of • Oracle data mining,
machine learning • Orange,
algorithms include: • Python scikit-learn,
• Ayasdi, • SAS Enterprise Miner,
• apache Mahout, • STATISTICA Data
• Gesture Recognition Miner and
Toolkit, • Weka.
• IBM SPSS Modeler,

Machine Learning

Uploaded by

Copyright:

Available Formats

Machine Learning

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Machine Learning

Uploaded by

Copyright:

Available Formats

BCS303

Performance is usually The key task is the

• stock market analysis, • affective computing

You might also like