UNIT-2

Introduction to AI Applications in Pharmacy

Introduction

Artificial Intelligence (AI) is a domain of computer science which deals with the development of
intelligent computer systems, which are capable to perceive, analyze, and react accordingly to the
inputs It is well-known fact that humans are considered as the most intelligent and smart species on
earth. The features which have helped them to bag this title include the ability to think, apply logic,
do reasoning, understand the complexity, and make decisions on their own

There are many areas which contribute to artificial intelligence which includes mathematics (used for
developing algorithms), biology, philosophy, psychology, neuroscience (for studying human mind
and its behavior), statistics (for handling huge data), and last but not the least, computer science (to
run the algorithm for implementing the concepts).

Types of AI (Based on Capabilities)

The various types of artificial intelligence based on the capabilities can be classified as

--Weak or narrow AI

– General AI

– Strong AI.

Weak or narrow AI: it is a type of AI which can perform a predefined narrow set of instructions
without exhibiting any thinking capability. It is the most widely used type of AI in this world. Some
famous examples are Apples’s Siri, Alexa, Alpha Go, IBM’s Watson supercomputer, Sophia (the
humanoid) all belong to the weak AI type.

General AI: it is the type of AI which can perform the tasks like what human can do. Till now it is
not achieved, there are no such machines which works like human or can think as perfectly as
human, but it may happen in near future.

Strong AI: it is the type of AI in which it is expected that the machine will surpass the capacity of
human. It will perform better than humans, though it is tough, but it is not impossible. It may be the
situation when it can be said that the machines will be the master and overtake humans.

Types of AI (Based on Functionality)

Based on the functionality, artificial intelligence can be classified as per the following types:

(i) Reactive machines

(ii) Limited memory

(iii) Theory of mind

(iv) Self-awareness
Reactive machines: These are the machines which works on the data available in the form of
predefined dataset. It does not have the facility of data storage for storing the past and future data. It
completely depends on the present data. IBM’s chess program which defeated famous champion
Garry Kasparov and the deep blue system, Google’s AlphaGo are some of the examples for reactive
machines.

Limited memory: these are the machines which can store the past experience or store the memory
for limited period of time. An example for limited memory AI is the self-driving cars (it can store the
information like speed, distance, speed limit required for the navigation of the car).

Theory of mind: these are types of machines, which are expected to understand the psychological
and emotional aspects of human mind and work accordingly. So far such machines are a dream but
scientists are working to develop such machines in near future.

Self-awareness: these machines belong to a hypothetical concept that will be considered as super-
intelligent machines, which can think, act, and will be self-aware as they will have consciousness and
sentiments like humans. Research is carried out to develop such machines and considered as future
AI.

Domains of AI

The major domains of AI (Fig. 1) are neural network, robotics, expert systems, fuzzy logic systems,
natural language processing (NLP).

Neural networks: these can be described as the representation of human neural system, i.e., neurons
and dendrites in the form of layers and nodes representing data. It comprises algorithms that
understand the relationships between the data while mimicking the human brain. These are widely
used in AI in the form of machine learning and deep learning. Some of the typical examples are
pattern recognition of face and image recognition in medical diagnosis.

Robotics: it is the domain of AI which is mostly associated with the development of intelligent
machines in the form of robot which obeys human instructions. The use of robots or humanoids is a
new trend and is being appreciated and adopted worldwide. Robots used in industry, medical
surgery, restaurants, etc., are classified under this category.

Expert system: these are systems which make decisions with the help of data present in the
knowledge base and getting guidance by an expert. These are basically computer applications
developed to solve complex problems with intelligence and expertise.

Fuzzy logic system: this domain is considered as resembling the human thinking method and
decision-making. It is quite similar to the way humans decide between 0 and 1, but it also deals with
all the possibilities between 0 and 1. Examples of fuzzy logic systems used are in consumer
electronics, automobiles, comparison of data, etc.

Natural language processing (NLP) is a machine learning technology that gives computers the
ability to interpret, manipulate, and comprehend human language. Organizations today have large
volumes of voice and text data from various communication channels like emails, text messages,
social media newsfeeds, video, audio, and more. They use NLP software to automatically process
this data, analyze the intent or sentiment in the message, and respond in real time to human
communication.
Subsets of Artificial Intelligence

Artificial intelligence has emerged as a boon for the society for the furtherance of advanced
techniques to deal with the real-life problems. The major two subsets of AI are Machine Learning
(ML) and Deep Learning (DL). ML is considered as the subset of AI and DL is considered as the
subset of ML.
Machine Learning:
As humans can think, improve by self-improvement cycle, and learn from the past
experiences, AI machines can also learn from the past experiences with the help of the concept
known as Machine Learning (ML). The machine learning deals with the development of algorithms
that enables the computer to learn from its data and past experiences on their own.
Classification of Machine Learning Based on the nature of the learning signal or response that the
machine gets; machine learning can be classified into following categories:
(i) Supervised learning
(ii) Unsupervised learning
(iii) Reinforcement learning
Supervised learning:
According to the literal meaning, this method correlates with the method of learning of student under
the supervision of a teacher. As a teacher illustrates the student with many good examples to help in
grasping the concept perfectly, the machine is provided with many labeled data to help in obtaining
the perfect output from the given input.
Unsupervised learning:
In this method the machine has to train itself without any supervisor, i.e., the data provided at the
input are not labeled or classified. The algorithm has to train itself by searching the degree of
similarities among the given data and figure out the appropriate output for the given problem.

Reinforcement learning:
This method is typically a feedback-based learning method. In this method the machine is given a
reward for every right action taken by it and a penalty for any wrong action, so it is a self-learning
method done by analyzing its past performances.
Challenges and limitation of ML:
1.The basic challenge and limitation for ML are that it requires huge amount of data. Without quality
data, ML algorithm cannot provide accurate results for further analysis. The prediction can be
considered best if the analysis is done over a large amount of data.
2.Another point is that the data need to be heterogeneous as well. With wide range of inputs or
datasets, the efficiency of the algorithm will be enhanced with appropriate output.

Deep Learning
Deep Learning (DL) is considered as the sub domain of ML and thereby the subset of AI. Deep
learning can be denoted as the next level of machine learning where the system is similar to human
nervous system and mimic the working of the neurons. As the number of layers increases, it is called
as deep learning or Deep Neural Network (DNN) . The initial layer is denoted as the input layer, the
last layer is called the output layer and the intermediate layers are termed as the hidden layer, where
all the layers are inter connected .
It helps in enhanced feature extraction, pattern recognition of complex dataset and high-level
data extraction. The main advantage is that it can learn without any predefined data and does not
require explicit programming by the programmers.
Problem Solving Techniques in AI
The process of problem-solving is frequently used to achieve objectives or resolve particular
situations. In computer science, the term "problem-solving" refers to artificial intelligence methods,
which may include formulating ensuring appropriate, using algorithms, and conducting root-cause
analyses that identify reasonable solutions. Artificial intelligence (AI) problem-solving often involves
investigating potential solutions to problems through reasoning techniques, making use of
polynomial and differential equations, and carrying them out and use modeling frameworks. A same
issue has a number of solutions, that are all accomplished using an unique algorithm. Additionally,
certain issues have original remedies. Everything depends on how the particular situation is framed.

Cases involving Artificial Intelligence Issues

Artificial intelligence is being used by programmers all around the world to automate systems for
effective both resource and time management. Games and puzzles can pose some of the most
frequent issues in daily life. The use of AI algorithms may effectively tackle this. Various problem-
solving methods are implemented to create solutions for a variety complex puzzles, includes
mathematics challenges such crypto-arithmetic and magic squares, logical puzzles including
Boolean formulae as well as N-Queens, and quite well games like Sudoku and Chess. Therefore,
these below represent some of the most common issues that artificial intelligence has remedied:

o Chess
o N-Queen problem
o Tower of Hanoi Problem
o Travelling Salesman Problem
o Water-Jug Problem

A Reflex Agent: But What's It?

Depending on their ability for recognizing intelligence, these five main artificial intelligence agents
were deployed today. The below would these be agencies:

o Simple Reflex Agents(a type of intelligent agent that performs actions based solely on the current
situation,)
o Model-Based Reflex Agents (one that uses internal memory and a percept history to create a
model of the environment in which it's operating and make decisions based on that model.)
o Goal-Based Agents(an intelligent program that can make decisions based on previous experiences,
knowledge, user input, and the desired goal)
o Utility-Based Agents(an agent that acts based not only on what the goal is, but the best way to
reach that goal)
o Learning Agents ( a tool in AI that is capable of learning from its experiences.)
This mapping of states and actions is made easier through these agencies. These agents frequently
make mistakes when moving onto the subsequent phase of a complicated issue; hence, problem-
solving standardized criteria such cases. Those agents employ artificial intelligence can tackle issues
utilising methods like B-tree and heuristic algorithms.

Approaches for Resolving Problems

The effective approaches of artificial intelligence make it useful for resolving complicated issues. All
fundamental problem-solving methods used throughout AI were listed below. In accordance with
the criteria set, students may learn information regarding different problem-solving methods.

Heuristics
The heuristic approach focuses solely upon experimentation as well as test procedures to
comprehend a problem and create a solution. These heuristics don't always offer better ideal answer
to something like a particular issue, though. Such, however, unquestionably provide effective means
of achieving short-term objectives. Consequently, if conventional techniques are unable to solve the
issue effectively, developers turn to them. Heuristics are employed in conjunction with optimization
algorithms to increase the efficiency because they merely offer moment alternatives while
compromising precision.

Searching Algorithms
Several of the fundamental ways that AI solves every challenge is through searching. These
searching algorithms are used by rational agents or problem-solving agents for select the most
appropriate answers. Intelligent entities use molecular representations and seem to be frequently
main objective when finding solutions. Depending upon that calibre of the solutions they produce,
most searching algorithms also have attributes of completeness, optimality, time complexity, and
high computational.

Computing Evolutionary
This approach to issue makes use of the well-established evolutionary idea. The idea of "survival of
the fittest underlies the evolutionary theory. According to this, when a creature successfully
reproduces in a tough or changing environment, these coping mechanisms are eventually passed
down to the later generations, leading to something like a variety of new young species. By
combining several traits that go along with that severe environment, these mutated animals aren't
just clones of something like the old ones. The much more notable example as to how development
is changed and expanded is humanity, which have done so as a consequence of the accumulation of
advantageous mutations over countless generations.

Genetic Algorithms
Genetic algorithms have been proposed upon that evolutionary theory. These programs employ a
technique called direct random search. In order to combine the two healthiest possibilities and
produce a desirable offspring, the developers calculate the fit factor. Overall health of each
individual is determined by first gathering demographic information and afterwards assessing each
individual. According on how well each member matches that intended need, a calculation is made.
Next, its creators employ a variety of methodologies to retain their finest participants.

1. Rank Selection
2. Tournament Selection
3. Steady Selection
4. Roulette Wheel Selection (Fitness Proportionate Selection)
5. Elitism

What is knowledge representation?

Humans are best at understanding, reasoning, and interpreting knowledge. Human knows things,
which is knowledge and as per their knowledge they perform various actions in the real world. But
how machines do all these things comes under knowledge representation and reasoning.
Hence we can describe Knowledge representation as following:

o Knowledge representation and reasoning (KR, KRR) is the part of Artificial intelligence which
concerned with AI agents thinking and how thinking contributes to intelligent behavior of
agents.
o It is responsible for representing information about the real world so that a computer can
understand and can utilize this knowledge to solve the complex real world problems such as
diagnosis a medical condition or communicating with humans in natural language.
o It is also a way which describes how we can represent knowledge in artificial intelligence.
Knowledge representation is not just storing data into some database, but it also enables an
intelligent machine to learn from that knowledge and experiences so that it can behave
intelligently like a human.

What to Represent:
Following are the kind of knowledge which needs to be represented in AI systems:

o Object: All the facts about objects in our world domain. E.g., Guitars contains strings,
trumpets are brass instruments.
o Events: Events are the actions which occur in our world.
o Performance: It describe behavior which involves knowledge about how to do things.
o Meta-knowledge: It is knowledge about what we know.
o Facts: Facts are the truths about the real world and what we represent.
o Knowledge-Base: The central component of the knowledge-based agents is the knowledge
base. It is represented as KB. The Knowledgebase is a group of the Sentences (Here,
sentences are used as a technical term and not identical with the English language).

Knowledge: Knowledge is awareness or familiarity gained by experiences of facts, data, and

situations. Following are the types of knowledge in artificial intelligence:
Types of knowledge
Following are the various types of knowledge:

1. Declarative Knowledge:

o Declarative knowledge is to know about something.

o It includes concepts, facts, and objects.
o It is also called descriptive knowledge and expressed in declarativesentences.
o It is simpler than procedural language.

2. Procedural Knowledge

o It is also known as imperative knowledge.

o Procedural knowledge is a type of knowledge which is responsible for knowing how to do
something.
o It can be directly applied to any task.
o It includes rules, strategies, procedures, agendas, etc.
o Procedural knowledge depends on the task on which it can be applied.

3. Meta-knowledge:

o Knowledge about the other types of knowledge is called Meta-knowledge.

4. Heuristic knowledge:

o Heuristic knowledge is representing knowledge of some experts in a filed or subject.

o Heuristic knowledge is rules of thumb based on previous experiences, awareness of
approaches, and which are good to work but not guaranteed.

5. Structural knowledge:

o Structural knowledge is basic knowledge to problem-solving.

o It describes relationships between various concepts such as kind of, part of, and grouping of
something.
o It describes the relationship that exists between concepts or objects.

AI knowledge cycle:

An Artificial intelligence system has the following components for displaying intelligent
behavior:

o Perception

o Learning

o Knowledge Representation and Reasoning

o Planning

o Execution

The above diagram is showing how an AI system can interact with the real world and what
components help it to show intelligence. AI system has Perception component by which it retrieves
information from its environment. It can be visual, audio or another form of sensory input. The
learning component is responsible for learning from data captured by Perception comportment. In the
complete cycle, the main components are knowledge representation and Reasoning. These two
components are involved in showing the intelligence in machine-like humans. These two
components are independent with each other but also coupled together. The planning and execution
depend on analysis of Knowledge representation and reasoning.