What is Learning for a machine?

A machine is said to be learning from past Experiences (data feed in) with

respect to some class of Tasks if it’s Performance in each Task improves with
the Experience.

 According to Herbert Simon, learning denotes changes in a system that

enable a system to do the same task more efficiently the next time.
 Arthur Samuel stated that, "Machine learning is the subfield of computer
science, that gives computers the ability to learn without being explicitly
programmed ".
 In 1997, Mitchell proposed that, " 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 ".
 The main purpose of machine learning is to study and design the algorithms
that can be used to produce the predicates from the given dataset.
 Besides these, the machine learning includes the agents percepts  for acting
as well as to improve their future performance.

A machine is said to be learning from past Experiences (data feed in) with

respect to some class of Tasks if it’s Performance in each Task improves with
the Experience.
For example, assume that a machine must predict whether a customer will buy a
specific product let’s say “Antivirus” this year or not.
The machine will do it by looking at the previous knowledge/past experiences
i.e., the data of products that the customer had bought every year and if he buys
Antivirus every year, then there is a high probability that the customer is going to
buy an antivirus this year as well. This is how machine learning works at the
basic conceptual level.
Learning is the process of converting experience into expertise or knowledge.

AI learning models can be classified in two main types: inductive and deductive.

— Inductive Learning: This type of AI learning model is based on inferring a

general rule from datasets of input-output pairs. Algorithms such as knowledge
based inductive learning (KBIL) are a great example of this type of AI learning
technique. KBIL focused on finding inductive hypotheses on a dataset with the help
of background information.

Specific to General

— Deductive Learning: This type of AI learning technique starts with the series of
rules and infers new rules that are more efficient in the context of a specific AI
algorithm.

General to Specific
Explanation-Based Learning (EBL) and Relevance-Based Learning (RBL) are
examples of deductive techniques. EBL extracts general rules from examples by
“generalizing” the explanation. RBL focuses on identifying attributes and deductive
generalizations from simple example.

Basis for Deductive Reasoning Inductive Reasoning

comparison

Definition Deductive reasoning is the Inductive reasoning arrives at a

form of valid reasoning, to conclusion by the process of
deduce new information or generalization using specific
conclusion from known facts or data.
related facts and information.

Approach Deductive reasoning follows a Inductive reasoning follows a

top-down approach. bottom-up approach.

Starts from Deductive reasoning starts Inductive reasoning starts from

from Premises. the Conclusion.
 Validity In deductive reasoning In inductive reasoning, the truth
conclusion must be true if the of premises does not guarantee
premises are true. the truth of conclusions.

Usage Use of deductive reasoning is Use of inductive reasoning is fast

difficult, as we need facts and easy, as we need evidence
which must be true. instead of true facts. We often
use it in our daily life.

Process Theory→ hypothesis→ Observations-

patterns→confirmation. →patterns→hypothesis→Theory.

Argument In deductive reasoning, In inductive reasoning,

arguments may be valid or arguments may be weak or
invalid. strong.

Structure Deductive reasoning reaches Inductive reasoning reaches from

from general facts to specific specific facts to general facts.
facts.

Supervised Learning:
Supervised learning is the types of machine learning in which machines are trained
using well "labelled" training data, and on basis of that data, machines predict
the output. The labelled data means some input data is already tagged with the
correct output.
In supervised learning, the training data provided to the machines work as the
supervisor that teaches the machines to predict the output correctly. It applies
the same concept as a student learns in the supervision of the teacher.
Supervised learning is a process of providing input data as well as correct output
data to the machine learning model. The aim of a supervised learning algorithm is
to find a mapping function to map the input variable(x) with the output
variable(y).
Regression trains on and predicts a continuous-valued response, for example
predicting real estate prices.
Classification attempts to find the appropriate class label, such as analyzing
positive/negative sentiment, male and female persons, benign and malignant
tumors, secure and unsecure loans etc.
Unsupervised Learning
Unsupervised learning is used to detect anomalies, outliers, such as fraud or
defective equipment, or to group customers with similar behaviors for a sales
campaign. It is the opposite of supervised learning. There is no labeled data here.
When learning data contains only some indications without any description or
labels, it is up to the coder or to the algorithm to find the structure of the
underlying data, to discover hidden patterns, or to determine how to describe
the data. This kind of learning data is called unlabeled data.

As the name suggests, unsupervised learning is a machine learning technique in

which models are not supervised using training dataset. Instead, models itself find
the hidden patterns and insights from the given data.
It can be compared to learning which takes place in the human brain while
learning new things.
It can be defined as: Unsupervised learning is a type of machine learning in
which models are trained using unlabeled dataset and can act on that data
without any supervision.
Unsupervised learning cannot be directly applied to a regression or classification
problem because unlike supervised learning, we have the input data but no
corresponding output data. The goal of unsupervised learning is to find the
underlying structure of dataset, group that data according to similarities, and
represent that dataset in a compressed format.

o Clustering: Clustering is a method of grouping the objects into clusters

such that objects with most similarities remains into a group and has less or
no similarities with the objects of another group. Cluster analysis finds the
commonalities between the data objects and categorizes them as per the
presence and absence of those commonalities.
o Association Rule Generation: An association rule is an unsupervised
learning method which is used for finding the relationships between
variables in the large database. It determines the set of items that occurs
together in the dataset. Association rule makes marketing strategy more
effective. Such as people who buy X item (suppose a bread) also tend to
purchase Y (Butter/Jam) item. A typical example of Association rule is
Market Basket Analysis.
Semi-supervised Learning
If some learning samples are labeled, but some other are not labeled, then it is
semi-supervised learning. It makes use of a large amount of unlabeled data for
training and a small amount of labeled data for testing. Semi-supervised
learning is applied in cases where it is expensive to acquire a fully labeled dataset
while more practical to label a small subset. For example, it often requires skilled
experts to label certain remote sensing images, and lots of field experiments to
locate oil at a particular location, while acquiring unlabeled data is relatively easy.

In this type of learning, the algorithm is trained upon a combination of labeled

and unlabeled data. Typically, this combination will contain a very small
amount of labeled data and a very large amount of unlabeled data.
The basic procedure involved is that first, the programmer will cluster similar
data using an unsupervised learning algorithm and then use the existing labeled
data to label the rest of the unlabeled data.
The typical use cases of such type of algorithm have a common property among
them – The acquisition of unlabeled data is relatively cheap while labeling the
said data is very expensive.
Intuitively, one may imagine the three types of learning algorithms as
Supervised learning where a student is under the supervision of a teacher at both
home and school, Unsupervised learning where a student has to figure out a
concept himself and Semi-Supervised learning where a teacher teaches a few
concepts in class and gives questions as homework which are based on
similar concepts.

Reinforcement Learning

Reinforcement learning is an area of Machine Learning. It is about taking

suitable action to maximize reward in a particular situation.
It is employed by various software and machines to find the best possible
behavior or path it should take in a specific situation.
Reinforcement learning differs from the supervised learning in a way that in
supervised learning the training data has the answer key with it so the model is
trained with the correct answer itself whereas in reinforcement learning, there is
no answer but the reinforcement agent decides what to do to perform the given
task.
In the absence of a training dataset, it is bound to learn from its experience.

Here learning data gives feedback so that the system adjusts to dynamic
conditions in order to achieve a certain objective. The system evaluates its
performance based on the feedback responses and reacts accordingly. The best-
known instances include self-driving cars and chess master algorithm AlphaGo.
Types of Reinforcement: There are two types of Reinforcement:

1. Positive –
Positive Reinforcement is defined as when an event, occurs due to a particular
behavior, increases the strength and the frequency of the behavior. In other
words, it has a positive effect on behavior.
Advantages of reinforcement learning are:
 Maximizes Performance
 Sustain Change for a long period of time
Disadvantages of reinforcement learning:
 Too much Reinforcement can lead to overload of states which
can diminish the results.
2. Negative –
Negative Reinforcement is defined as strengthening of a behavior because a
negative condition is stopped or avoided.
Advantages of reinforcement learning:
 Increases Behavior
 Provide defiance to minimum standard of performance.
Disadvantages of reinforcement learning:
 It Only provides enough to meet up the minimum behavior.

Various Practical applications of Reinforcement Learning –

 RL can be used in robotics for industrial automation.
 RL can be used in machine learning and data processing.
 RL can be used to create training systems that provide custom
instruction and materials according to the requirement of students.

RL can be used in large environments in the following situations:

1. A model of the environment is known, but an analytic solution is not
available.
2. Only a simulation model of the environment is given (the subject of
simulation-based optimization)
3. The only way to collect information about the environment is to interact
with it.

ROTE LEARNING:
Rote learning is the process of memorizing information based on repetition.
Rote learning enhances students’ ability to quickly recall basic facts and helps
develop foundational knowledge of a topic.
Examples of rote learning include memorizing multiplication tables or the
periodic table of elements. The drawbacks of rote learning are that it can be
repetitive, it’s easy to lose focus and it doesn’t allow for a deeper understanding of
a topic.
Idea behind is one should be able to recall material quicker the more one repeats
it.
Rote memorization isn’t considered higher-level thinking or critical thinking since
students don’t learn how to think, analyze, or solve problems with this type of
learning.

Rote Learning in Computer Science:

Rote learning is also used to describe a simple learning pattern used in machine
learning, although it does not involve repetition, unlike the usual meaning of rote
learning.
The machine is programmed to keep a history of calculations and compare new
input against its history of inputs and outputs, retrieving the stored output if
present.
This pattern requires that the machine can be modeled as a pure function — always
producing same output for same input — and can be formally described as follows:

Memoization
In computing, Memoization or memoisation is an optimization technique used
primarily to speed up computer programs by storing the results of
expensive function calls and returning the cached result when the same inputs
occur again. Memoization has also been used in other contexts (and for purposes
other than speed gains), such as in simple mutually recursive descent parsing.
[1]
 Although related to caching, memorization refers to a specific case of this
optimization, distinguishing it from forms of caching such as buffering or page
replacement. In the context of some logic programming languages, Memoization is
also known as tabling
A memoized function "remembers" the results corresponding to some set of
specific inputs. Subsequent calls with remembered inputs return the
remembered result rather than recalculating it, thus eliminating the primary
cost of a call with given parameters from all but the first call made to the
function with those parameters. The set of remembered associations may be a
fixed-size set controlled by a replacement algorithm or a fixed set, depending on
the nature of the function and its use. A function can only be memoized if it
is referentially transparent; that is, only if calling the function has the same effect
as replacing that function call with its return value. (Special case exceptions to this
restriction exist, however.) While related to lookup tables, since memoization often
uses such tables in its implementation, memoization populates its cache of results
transparently on the fly, as needed, rather than in advance.
Memoization is a way to lower a function's time cost in exchange for space cost;
that is, memoized functions become optimized for speed in exchange for a higher
use of computer memory space. The time/space "cost" of algorithms has a specific
name in computing: computational complexity. All functions have a computational
complexity in time (i.e. they take time to execute) and in space.
Although a space–time tradeoff occurs (i.e., space used is speed gained), this
differs from some other optimizations that involve time-space trade-off, such
as strength reduction, in that memoization is a run-time rather than compile-
time optimization. Moreover, strength reduction potentially replaces a costly
operation such as multiplication with a less costly operation such as addition, and
the results in savings can be highly machine-dependent (non-portable across
machines), whereas memoization is a more machine-independent, cross-
platform strategy.

Learning by Taking Advice:

 This type is the easiest and simple way of learning.

 In this type of learning, a programmer writes a program to give some
instructions to perform a task to the computer. Once it is learned (i.e.
programmed), the system will be able to do new things.
 Also, there can be several sources for taking advice such as
humans(experts), internet etc.
  However, this type of learning has a more necessity of inference than rote
learning.
 As the stored knowledge in knowledge base gets transformed into an
operational form, the reliability of the knowledge source is always taken
into consideration.

Explanation Based Learning:

 Explanation-based learning (EBL) deals with an idea of
single-example learning.
 This type of learning usually requires a substantial number
of training instances but there can be some difficulties in
this like it is difficult to have such number of training
instances.
 Sometimes, it may help us to learn certain things
effectively, especially when we have enough knowledge.  

Hence, instance-based learning is more data-intensive,

data-driven while EBL is more knowledge-intensive,
knowledge-driven.
 Initially, an EBL system accepts a training example.
 Based on the given goal concept, an operationality criteria
and domain theory, it "generalizes" the training example to
describe the goal concept and to satisfy the operationality
criteria (which are usually a set of rules that describe
relationships between objects and actions in a domain).
 Thus, several applications are possible for the knowledge
acquisition and engineering aspects.

Learning in Problem Solving

 Humans have a tendency to learn by solving various
real-world problems.
 The forms or representation, or the exact entity, problem
solving principle is based on reinforcement learning.
 Therefore, repeating certain action results in desirable
outcome while the action is avoided if it results into
undesirable outcomes.
 As the outcomes must be evaluated, this type of learning
also involves the definition of a utility function. This
function shows how much is a particular outcome
worth?
 There are several research issues which include the
identification of the learning rate, time and algorithm
complexity, convergence, representation (frame and
qualification problems), handling of uncertainty
(ramification problem), adaptivity and "unlearning" etc.
 In reinforcement learning, the system (and thus the
developer) knows the desirable outcomes but does not
know which actions result into desirable outcomes.
 In such a problem or domain, the effects of performing the
actions are usually compounded with side-effects. Thus, it
becomes impossible to specify the actions to be performed
in accordance with the given parameters.
https://www.tutorialride.com/artificial-intelligence/learning-and-expert-system-in-
ai.htm