Scribd
Upload
7 views

Learning

Uploaded by

radhikasn
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
7 views

Learning

Uploaded by

radhikasn
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

BASICS OF LEARNING

THEORY
What is learning?

”The activity or process of gaining knowledge or skill by


studying, practicing, being taught, or experiencing something.”
--Merriam Webster dictionary

“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.”
------Tom Mitchell
How Computer learn?
It depends on nature of the problem that computer can solve

Two kinds of problem :


1. Well posed
2. Ill posed
The following components inherent to it.
• class of learning tasks (T)
• A measure of performance (P)
• A source of experience (E)

“A program can learn from E for the task T, and P improves with experience E”
Let x input and X be the input space, which is the set of all inputs,
and Y is the output space, which is the set of all possible outputs, that
is, yes/no.
learning model can be stated as follows:

Learning Model =Hypothesis Set+ Leaming Algorithm


Classical and Adaptive Machine Learning
systems
• A classical machine learning system has components such as
Input, Process and Output.

• Adaptive systems interact with the input for getting labelled


data as direct inputs are not available. This process is called
reinforcement learning.
Learning Types
1. Learn By Memorization Or Learn By Repetition

2. Learn By Examples Also Called As Learn By Experience

3. Learn By Being Taught

4. Learning By Critical Thinking

5. Self Learning, Also Called As Reinforcement Learning

6. Learning_ To Solve_ Problems

7. Learning By Generalizing Explanations


INTRODUCTION TO COMPUTATION LEARNING
THEORY
• How can a learning system predict an unseen instance?
• How do the hypothesis h is close to f, when hypothesis f itself is
unknown?
• How many samples are required?
• Can we measure the performance of a learning system?
• Is the solution obtained local or global?
• These questions are the basis of a field called
'Computational learning Theory or in short (COLT).
• COLT deals with formal methods used for learning systems.

• It provides a fundamental basis for study of machine learning. It deals


with Probably Approximate Leaming (PAC) and Vapnik-Chervonenkis
(VC) dimensions.

• The focus of PAC is the quantification of the computational difficulty


of learning tasks and algorithms and the computation capacity
quantification is the focus of VC dimension.
DESIGN OF A LEARNING SYSTEM

• A system that is built around a learning algorithm is called a learning


system.

• The design of systems focuses on these steps:


• Choosing a training experience

• Choosing a target function

• Representation of a target function

• Function approximation
Thus, the learning system has the following components:

• A Performance system to allow the game to play against itself.

• A Critic system to generate the samples.

• A Generalizer system to generate a hypothesis based on samples.

• An Experimenter system to generate a new system based on the


currently learnt function. This is sent as input to the performance
system.
INTRODUCTION TO CONCEPT LEARNING
• Concept learning is a learning strategy of acquiring abstract knowledge or inferring a
genera} concept or deriving a category from the given training samples. It is a process of
abstraction and generalization from the data.
• Concept learning requires three things:
• Input - Training dataset which is a set of training instances, each labeled with the
name of a concept or category to which it belongs. Use this past experience to
train and build the model.
• Output - Target concept or Target function f It is a mapping functionf(x) from
input x to output y. It is to determine the specific features or common features to
identify an object. In other words, it is to find the hypothesis to determine the
target concept For e.g., the specific set of features to identify an elephant from all
animals.
• Test - New instances to test the learned model.
• lec01-conceptLearning.pdf

You might also like