100% found this document useful (1 vote)
147 views15 pages

Machine Learning: Presentation By: C. Vinoth Kumar SSN College of Engineering

Machine learning is a branch of artificial intelligence that allows systems to learn from data and experience to improve their performance on tasks. The goal is to build systems that can learn from their experience to optimize a performance function. Machine learning can be used to extract knowledge from data, learn tasks that are difficult to formalize, and create software that improves over time. There are supervised and unsupervised learning approaches, and machine learning has applications in areas like speech recognition, data mining, games, and medical diagnosis.

Uploaded by

Lekshmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
100% found this document useful (1 vote)
147 views15 pages

Machine Learning: Presentation By: C. Vinoth Kumar SSN College of Engineering

Machine learning is a branch of artificial intelligence that allows systems to learn from data and experience to improve their performance on tasks. The goal is to build systems that can learn from their experience to optimize a performance function. Machine learning can be used to extract knowledge from data, learn tasks that are difficult to formalize, and create software that improves over time. There are supervised and unsupervised learning approaches, and machine learning has applications in areas like speech recognition, data mining, games, and medical diagnosis.

Uploaded by

Lekshmi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 15

Machine Learning

Presentation by:
C. Vinoth Kumar
SSN College of Engineering
Machine learning Basics

 The goal of machine learning is to build computer


systems that can adapt and learn from their experience
to optimize a performance function.

 It is a branch of Artificial Intelligence.

 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.
Machine learning Basics

 It can be used to
• Extract knowledge from data
• Learn tasks that are difficult to formalize
• Create software that improves over time

 The learning is required when


• Human expertise does not exist (navigating on Mars)
• Humans are unable to explain their expertise (speech
recognition)
• Solution changes in time (routing on a computer
network)
• Solution needs to be adapted to particular cases
(user biometrics)
Machine learning

 Machine learning is important because,

• Some tasks cannot be defined well, except by examples.


• Machine learning can be used to extract the relationships
and correlations which are hidden within data.
• The amount of knowledge available about certain tasks
might be too large for explicit encoding by humans (e.g.,
medical diagnostic).
• Human designers often produce machines that do not
work as well as desired in the environments in which they
are used.
• 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”.
Classification of learning

 Based on the type of result expected from the algorithm


1. Classification problems: handwriting recognition,
digit recognition, Supervised learning, speech
recognition
2. Decision problems: Speech recognition, Robots,
Game playing

 Based on Agent
1. Supervised learning: having a supervisor who tell
the agent whether or not the result is correct, e.g.
neural networks
2. Unsupervised learning: there are no supervisor, e.g.
clustering
Machine learning

 Examples:

1. Learning to recognize spoken words


2. Learning to drive an autonomous vehicle
3. Learning to classify new astronomical structures
4. Learning to play world-class backgammon
5. Learning to classify chemical compounds
6. Learning to drive an autonomous vehicle
7. Learning to play bridge
8. Learning to parse natural language sentences, etc.
Machine learning Applications

• Speech and hand-writing recognition


• Autonomous robot control
• Data mining and bioinformatics: motifs, alignment, …
• Playing games
• Fault detection
• Clinical diagnosis
• Spam email detection
• Credit scoring, fraud detection
• Web mining: search engines
• Market basket analysis

Applications are diverse but methods are generic.


Areas of Influence for Machine Learning

 Statistics: How best to use samples drawn from unknown


probability distributions to help decide from which distribution some
new sample is drawn?
 Brain Models: Non-linear elements with weighted inputs (Artificial
Neural Networks) have been suggested as simple models of
biological neurons.
 Adaptive Control Theory: How to deal with controlling a process
having unknown parameters that must be estimated during
operation?
 Psychology: How to model human performance on various learning
tasks?
 Artificial Intelligence: How to write algorithms to acquire the
knowledge humans are able to acquire, at least, as well as
humans?
 Evolutionary Models: How to model certain aspects of biological
evolution to improve the performance of computer programs?
Benefits of Machine learning

 Makes human-computer interaction easier

 Relatively simple to integrate

 Will distinguish your product from others

 Increase customer satisfaction

 Will improve simple intelligent systems (ex:


Microsoft Word’s grammar checker)

 Easy to migrate to new domains


Designing a Learning System – An Example

1. Problem Description

2. Choosing the Training Experience

3. Choosing the Target Function

4. Choosing a Representation for the Target Function

5. Choosing a Function Approximation Algorithm

6. Final Design
Machine learning Algorithm

 Generalization is the ability of an algorithm to perform


accurately on new, unseen examples after having
trained on a learning data set.

 The core objective of a learner is to generalize from its


experience.

 The training examples come from some generally


unknown probability distribution and the learner has to
extract from them something more general, something
about that distribution, that allows it to produce useful
predictions in new cases.
Machine learning Algorithm

 In order to learn the (approximated) target function we


require:

1. A set of training examples (input arguments)

2. A rule for estimating the value corresponding to each


training example (if this is not directly available)

3. An algorithm for choosing the function that best fits


the training data
Machine learning Algorithm

 Supervised learning: Let X and Y be the set of possible


inputs and outputs, respectively.

1. Target function: Function f from X to Y.

2. Training data: Finite sequence D of pairs {x, f(x)} (x ϵ


X).

3. Hypothesis space: Subset H of functions from X to Y.

4. Learning algorithm: Function A mapping a training


set D to a hypothesis h ϵ H.
Machine learning Algorithm

 Unsupervised learning: Learning without output values


(data exploration, e.g. clustering).
 Query learning: Learning where the learner can query
the environment about the output associated with a
particular input.
 Reinforcement learning: Learning where the learner has
a range of actions which it can take to attempt to move
towards states where it can expect high rewards.
 Batch vs. online learning: All training examples at once
or one at a time (with estimate and update after each
example).
 Concept learning: Inferring a Boolean-valued function
from training examples of its input and output.
Issues in Machine Learning

 What algorithms are available for learning a concept?


How well do they perform?

 How much training data is sufficient to learn a concept


with high confidence?

 When is it useful to use prior knowledge?

 Are some training examples more useful than others?

 What are best tasks for a system to learn?

 What is the best way for a system to represent its


knowledge?

You might also like