3. Machine Learning
11-Oct-17
The problems of our human limitations go away if we
can make computers do the dirty things for us.
This is why machine learning is so popular.
Humans can: think, learn, see, understand language,
reason, etc.
Artificial Intelligence aims to reproduce these
capabilities.
Machine Learning is one part of Artificial
Intelligence. 3
4. What is Learning?
11-Oct-17
Learning is any process by which a system
improves performance from experience.
Humans and other animals can display
behaviors that we label as intelligent by
learning from experience.
Learning a set of new facts
Learning how to do something
Improving ability of something already learned
4
5. Ways humans learn things
11-Oct-17
Talking, Walking, Running (Learning by mimicking,
reading or being told facts)
Tutoring (Being informed when one is correct)
Experience (Feedback from the environment)
Analogy (Comparing certain features of existing
knowledge to new problems)
Self-reflection (Thinking things in ones own mind,
deduction, discovery)
5
6. Important parts of Learning
11-Oct-17
Remembering: Recognizing that last time we were
in this situation, we tried out some particular
action, and it worked.
Adapting: So, we will try it again, or it didn’t work,
so we will try something different.
Generalizing: Recognizing similarity between
different situations, so that things that applied in
one place can be used in another.
6
7. Machine Learning
11-Oct-17
Ever since computers were invented, we have
wondered whether they might be made to learn.
The ability of a program to learn from experience —
that is, to modify its execution on the basis of newly
acquired information.
Machine learning is about automatically extracting
relevant information from data and applying it to
analyze new data.
7
8. Machine Learning (Definition)
11-Oct-17
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.
Arthur Samuel (1959). Machine Learning: Field of
study that gives computers the ability to learn without
being explicitly programmed.
Optimize a performance criterion using example data
or past experience. 8
9. What is the Learning
Problem?
11-Oct-17
Learning = Improving with experience
at some task
Improve over task T
With respect to performance measure P
Based on experience E
9
11. Types of Machine Learning
11-Oct-17
Supervised learning: Training data includes
desired outputs. Based on this training set, the
algorithm generalizes to respond correctly to all
possible inputs.
Unsupervised learning: Training data does not
include desired outputs, instead the algorithm tries
to identify similarities between the inputs that have
something in common are categorized together.
11
12. Types of Machine Learning
11-Oct-17
Reinforcement learning: (Rewards from policy) Reinforcement
learning is learning what to do--how to map situations to actions--so
as to maximize a numerical reward signal. The agent acts on its
environment, it receives some evaluation of its action
(reinforcement), but is not told of which action is the correct one to
achieve its goal; but instead The learner must discover which actions
yield the most reward by trying them.
Evolutionary learning: Biological organisms adapt to improve their
survival rates and chance of having offspring in their environment,
using an idea of fitness (how good the current solution is). This type
of learning is inspired by biological evolution such as reproduction,
mutation, recombination, natural selection and survival of the fittest.
12
16. Regression
11-Oct-17
A technique for determining
the statistical relationship
between two or more
variables where a change in
a dependent variable is
associated with, and
depends on, a change in one
or more independent
variables.
16