Q11​.

E
​ xplain Optimal A* algorithm ?
Q12​. ​ What is dynamic neural network?
Dynamic neural networks address nonlinear multivariate behaviour and include (learning of)
time-dependent behaviour, such as transient phenomena and delay effects. Techniques to estimate
a system process from observed data fall under the general category of system identification.

Cascading
Cascade correlation is an architecture and ​supervised learning​ ​algorithm​. Instead of just adjusting
the weights in a network of fixed topology, Cascade-Correlation begins with a minimal network, then
automatically trains and adds new hidden units one by one, creating a multi-layer structure. Once a
new hidden unit has been added to the network, its input-side weights are frozen. This unit then
becomes a permanent feature-detector in the network, available for producing outputs or for creating
other, more complex feature detectors. The Cascade-Correlation architecture has several
advantages: It learns quickly, determines its own size and topology, retains the structures it has built
even if the training set changes and requires no ​backpropagation​.

Neuro-fuzzy
A neuro-fuzzy network is a ​fuzzy​ ​inference system​ in the body of an artificial neural network.
Depending on the FIS type, several layers simulate the processes involved in a fuzzy inference-like
fuzzification, inference, aggregation and defuzzification. Embedding an FIS in a general structure of
an ANN has the benefit of using available ANN training methods to find the parameters of a fuzzy
system.

Compositional pattern-producing
Compositional pattern-producing networks (CPPNs) are a variation of artificial neural networks which
differ in their set of ​activation functions​ and how they are applied. While typical artificial neural
networks often contain only ​sigmoid functions​ (and sometimes ​Gaussian functions​), CPPNs can
include both types of functions and many others. Furthermore, unlike typical artificial neural
networks, CPPNs are applied across the entire space of possible inputs so that they can represent a
complete image. Since they are compositions of functions, CPPNs in effect encode images at infinite
resolution and can be sampled for a particular display at whatever resolution is optimal.
Q13​. ​ Make perceptron network for AND function?
Q14​. ​ Explain perceptron model with flowchart?
Q15​. ​Difference between batch and stochastic gradient
Descent?

Stochastic gradient descent (SGD or "on-line")​ typically reaches convergence much

faster than ​batch (or "standard") gradient descent​ since it updates weight more
frequently.

Unlike the ​batch gradient descent​ which computes the gradient using the whole
dataset, because the ​SGD​, also known as ​incremental gradient descent​, tries to find
minimums or maximums by iteration from a ​single​ randomly picked training example,
the error is typically noisier than in gradient descent.

However, this can also have the advantage that stochastic gradient descent can escape
shallow local minima more easily.

In order to obtain accurate results with stochastic gradient descent, the data sample
should be in a random order, and this is why we want to shuffle the training set for every
epoch.

The ​cost function​ to learn the weights for ​Adaline (Adaptive Linear Neuron)​ is
defined by associating with the ith observation in the training data set as:

where the ​ϕ i​ s an activation function.

To find the weights that minimize our cost function, we can use optimization
algorithm called ​gradient descent​:
Q16​. W
​ hat is mini batch gradient descent?
Q17​. W
​ hat is learning momentum gradient descent?
Q18​. W
​ hat is Iterative Deepening A* algorithm?
Q19​. ​What are linguistic hedges in fuzzy logic?
Q20​. ​ Derive Transposition theorem in predicate logic?
Q21​. ​What is unification algorithm?
Q22.