SOFT COMPUTING ASSIGNMENT

UNIT 1

Q1.Explain about the various activation functions used in neural network.

A1.1. Sigmoid Function
In an ANN, the sigmoid function is a non-linear AF used primarily in feedforward

neural networks. It is a differentiable real function, defined for real input values,

and containing positive derivatives everywhere with a specific degree of

smoothness. The sigmoid function appears in the output layer of the deep

learning models and is used for predicting probability-based outputs. The sigmoid

function is represented as:

2. Hyperbolic Tangent Function (Tanh)

The hyperbolic tangent function, a.k.a., the tanh function, is another type of AF. It

is a smoother, zero-centered function having a range between -1 to 1. As a

result, the output of the tanh function is represented by:

3. Softmax Function
The softmax function is another type of AF used in neural networks to compute

probability distribution from a vector of real numbers. This function generates an

output that ranges between values 0 and 1 and with the sum of the probabilities

being equal to 1. The softmax function is represented as follows:

4. Softsign Function

The softsign function is another AF that is used in neural network computing.

Although it is primarily in regression computation problems, nowadays it is also

used in DL based text-to-speech applications. It is a quadratic polynomial,

represented by:

5. Rectified Linear Unit (ReLU) Function

One of the most popular AFs in DL models, the rectified linear unit (ReLU)

function, is a fast-learning AF that promises to deliver state-of-the-art

performance with stellar results. Compared to other AFs like the sigmoid and

tanh functions, the ReLU function offers much better performance and

generalization in deep learning. The function is a nearly linear function that

 retains the properties of linear models, which makes them easy to optimize with

gradient-descent methods.

The ReLU function performs a threshold operation on each input element where

all values less than zero are set to zero. Thus, the ReLU is represented as:

6. Exponential Linear Units (ELUs) Function

The exponential linear units (ELUs) function is an AF that is also used to speed

up the training of neural networks (just like ReLU function). The biggest

advantage of the ELU function is that it can eliminate the vanishing gradient

problem by using identity for positive values and by improving the learning

characteristics of the model.

The exponential linear unit function is represented as:

Q2.Difference between soft computing and hard computing.

A2.1. Hard computing is best for solving the mathematical problems which don’t solve

the problems of the real world.

Soft computing is better used in solving real-world problems as it is stochastic in nature

i.e., it is a randomly defined process that can be analyzed statistically but not with

precision.

2. Hard computing relies on binary logic and predefined instructions like a numerical

analysis and brisk software and uses two-valued logic.

Soft computing is based on the model of the human mind where it has probabilistic

reasoning, fuzzy logic, and uses multivalued logic.

3. Hard computing needs exact input of the data and is sequential; on the other hand,

Soft computing can handle an abundance of data and handles multiple computations

which might not be exact in a parallel way.

4. Hard computing takes a lot of time to complete tasks and is costly while soft

computing tolerance of uncertainty and imprecision is estimated to achieve Machine

Intelligence Quotient (MIQ) and lower cost. It also provides better communication.

5. Hard computing is best suited for solving mathematical problems which give some

precise answers.

Soft computing resolves the nonlinear issues that involve uncertainty and impreciseness

as it has human-like intelligence that can resolve the real-life issue.

6. Hard computing takes a lot of time in computing as it requires the stated analytical

model and the model soft computing is based on is that of human intelligence.
 UNIT 2

Q1.Describe self organizing maps.

A1.The Self-Organizing Map is one of the most popular neural network models. It

belongs to the category of competitive learning networks. The Self-Organizing Map is

based on unsupervised learning, which means that no human intervention is needed

during the learning and that little needs to be known about the characteristics of the

input data. We could, for example, use the SOM for clustering data without knowing the

class memberships of the input data. The SOM can be used to detect features inherent

to the problem and thus has also been called SOFM, the Self-Organizing Feature Map.

The Self-Organizing Map was developed by professor Kohonen . The SOM has been

proven useful in many applications .

The SOM algorithm is based on unsupervised, competitive learning. It provides a

topology preserving mapping from the high dimensional space to map units. Map units,

or neurons, usually form a two-dimensional lattice and thus the mapping is a mapping

from high dimensional space onto a plane. The property of topology preserving means

that the mapping preserves the relative distance between the points. Points that are

near each other in the input space are mapped to nearby map units in the SOM. The

SOM can thus serve as a cluster analyzing tool of high-dimensional data. Also, the

SOM has the capability to generalize. Generalization capability means that the network

can recognize or characterize inputs it has never encountered before. A new input is

assimilated with the map unit it is mapped to.

The Self-Organizing Map is a two-dimensional array of neurons:

Q2.Give the limitations and application of Hopfield Network.

A2.It has been reported through simulations that Hopfield networks for crossbar
switching almost always achieve the maximum throughput. It has therefore appeared
that Hopfield networks of high-speed computation by parallel processing could possibly
be used for crossbar switching. However, it has not been determined whether they can
always achieve the maximum throughput. In the paper, the capabilities and limitations of
a Hopfield network for crossbar switching are considered. The Hopfield network
considered in the paper is generated from the most familiar and seemingly the most
powerful neural representation of crossbar switching. Based on a theoretical analysis of
the network dynamics, we show what switching control the Hopfield network can or
cannot produce. Consequently, we are able to show that a Hopfield network cannot
always achieve the maximum throughput.

UNIT 3

Q1.Define crisp sets with its fundamental concepts.

A1.Crisp sets are the sets that we have used most of our life. In a crisp set, an
element is either a member of the set or not. For example, a jelly bean belongs in the
class of food known as candy. Mashed potatoes do not. Fuzzy sets, on the other hand,
allow elements to be partially in a set.

Set Theory and Sets are one of the fundamental and widely present concepts in
mathematics. A Crisp Setor simple a Set is a well-defined collection of distinct objects
where each object is considered in its own right. Here are the 11 main properties/laws of
crisp sets:
Law of Commutativity:

● (A ∪ B) = (B ∪ A)
● (A ∩ B) = (B ∩ A)
Law of Associativity:

● (A ∪ B) ∪ C = A ∪ (B ∪ C)
● (A ∩ B) ∩ C = A ∩ (B ∩ C)

Law of Distributivity:

● A ∪ (B ∩ C) = (A ∪ B) ∩ (A ∪ C)
● A ∩ (B ∪ C) = (A ∩ B) ∪ (A ∩ C)

Idempotent Law

● A∪A=A
● A∩A=A

Identity Law

● A ∪ Φ = A => A ∪ E = E
● A ∩ Φ = Φ => A ∩ E = A

Here Φ is empty set and E is universal set or universe of discourse.

Law of Absorption

If A is a subset of B and conversely B is a superset of A then

● A ∪ (A ∩ B) = A
● A ∩ (A ∪ B) = A

Involution Law
 ● (Ac)c = A

Law of Transitivity

● If A ⊆ B, B ⊆ C, then A ⊆ C

Law of Excluded Middle

● (A ∪ Ac) = E

Law of Contradiction

● (A ∩ Ac) = Φ

De morgan laws

● (A ∪ B)c = Ac ∩ Bc
● (A ∩ B)c = Ac ∪ Bc

Q2.Explain the working of simplified fuzzy ART MAP.

A2.The presentation order of training patterns to a simplified fuzzy ARTMAP (SFAM)

neural network affects the classification performance. The common method to solve this

problem is to use several simulations with training patterns presented in random order,

where voting strategy is used to compute the final performance. Recently, an ordering

method based on min–max clustering was introduced to select the presentation order of
training patterns based on a single simulation. In this paper, another single simulation

method based on genetic algorithm is proposed to obtain the presentation order of

training patterns for improving the performance of SFAM. The proposed method is

applied to a 40-class individual classification problem using visual evoked potential

signals and three other datasets from UCI repository. The proposed method has the

advantages of improved classification performance, smaller network size and lower

training time compared to the random ordering and min–max methods. When compared

to the random ordering method, the new ordering scheme has the additional advantage

of requiring only a single simulation. As the proposed method is general, it can also be

applied to a fuzzy ARTMAP neural network when it is used as a classifier.

UNIT 4

Q1.What is fitness function? Why it is necessary?

A2.Fitness Function (also known as the Evaluation Function) evaluates how close a
given solution is to the optimum solution of the desired problem. It determines how fit a
solution is.In genetic algorithms, each solution is generally represented as a string of
binary numbers, known as a chromosome. We have to test these solutions and come
up with the best set of solutions to solve a given problem. Each solution, therefore,
needs to be awarded a score, to indicate how close it came to meeting the overall
specification of the desired solution. This score is generated by applying the fitness
function to the test, or results obtained from the tested solution.The following
requirements should be satisfied by any fitness function.

1. The fitness function should be clearly defined. The reader should be able to
clearly understand how the fitness score is calculated.
 2. The fitness function should be implemented efficiently. If the fitness function
becomes the bottleneck of the algorithm, then the overall efficiency of the
genetic algorithm will be reduced.
3. The fitness function should quantitatively measure how fit a given solution is
in solving the problem.
4. The fitness function should generate intuitive results. The best/worst
candidates should have best/worst score values.
Q2.What is reproduction? Give various methods of selecting chromosomes for
parent to crossover?
A2.In genetic algorithms and evolutionary computation, crossover, also called recombination, is a
genetic operator used to combine the genetic information of two parents to generate new offspring. It
is one way to stochastically generate new solutions from an existing population, and is analogous to
the crossover that happens during sexual reproduction in biology. Solutions can also be generated
by cloning an existing solution, which is analogous to asexual reproduction. Newly generated
solutions are typically mutated before being added to the population.

Different algorithms in evolutionary computation may use different data structures to store genetic
information, and each genetic representation can be recombined with different crossover operators.
Typical data structures that can be recombined with crossover are bit arrays, vectors of real
numbers, or trees.

UNIT 5

Q1.Explain Ant Colony Optimization.

A1.Ant colony optimization (ACO) is a population-based metaheuristic that can be

used to find approximate solutions to difficult optimization problems.

In ACO, a set of software agents called artificial ants search for good solutions to a
given optimization problem. To apply ACO, the optimization problem is transformed into
the problem of finding the best path on a weighted graph. The artificial ants (hereafter
ants) incrementally build solutions by moving on the graph. The solution construction
process is stochastic and is biased by a pheromone model, that is, a set of parameters
associated with graph components (either nodes or edges) whose values are modified
at runtime by the ants.
The easiest way to understand how ant colony optimization works is by means of an
example. We consider its application to the traveling salesman problem (TSP). In the
TSP a set of locations (e.g. cities) and the distances between them are given. The
problem consists of finding a closed tour of minimal length that visits each city once and
only once.

To apply ACO to the TSP, we consider the graph defined by associating the set of cities
with the set of vertices of the graph. This graph is called construction graph. Since in the
TSP it is possible to move from any given city to any other city, the construction graph is
fully connected and the number of vertices is equal to the number of cities. We set the
lengths of the edges between the vertices to be proportional to the distances between
the cities represented by these vertices and we associate pheromone values and
heuristic values with the edges of the graph. Pheromone values are modified at runtime
and represent the cumulated experience of the ant colony, while heuristic values are
problem dependent values that, in the case of the TSP, are set to be the inverse of the
lengths of the edges.

The ants construct the solutions as follows. Each ant starts from a randomly selected
city (vertex of the construction graph). Then, at each construction step it moves along
the edges of the graph. Each ant keeps a memory of its path, and in subsequent steps it
chooses among the edges that do not lead to vertices that it has already visited. An ant
has constructed a solution once it has visited all the vertices of the graph. At each
construction step, an ant probabilistically chooses the edge to follow among those that
lead to yet unvisited vertices. The probabilistic rule is biased by pheromone values and
heuristic information: the higher the pheromone and the heuristic value associated to an
edge, the higher the probability an ant will choose that particular edge. Once all the ants
have completed their tour, the pheromone on the edges is updated. Each of the
pheromone values is initially decreased by a certain percentage. Each edge then
receives an amount of additional pheromone proportional to the quality of the solutions
to which it belongs (there is one solution per ant).

This procedure is repeatedly applied until a termination criterion is satisfied.

Q2.What is Swarm Intelligence? Explain its techniques.
A2.Swarm intelligence (SI) is in the field of artificial intelligence (AI) and is based on the
collective behavior of elements in decentralized and self-organized systems. SI has a
great involvement in the field of Internet of Things (IoT) and IoT-based systems in order
to logically control their operations. As IoT-based systems are complex and consist of
smart objects, so powerful decentralized algorithms supported by SI are used to resolve
such complex problems. Intelligent algorithms of SI can solve the challenging issues of
IoT systems due to their dynamic properties, device mobility, wireless communication,
and information provision. SI algorithms are well established and applied in well-known
aptitude-based problems where real-time actions are handled efficiently. SI algorithms
like ant colony optimization, artificial bee colony, and social spider optimization play
important roles in normalizing the IoT processes. The current chapter covers the
technical understanding of the execution of SI and performs an analytical review of the
technology-based advanced applications of IoT supported by very logical SI
approaches.