1. Neural networks are computing systems
with interconnected nodes that work much
like neurons in the human brain. Using
algorithms, they can recognize hidden
patterns and correlations in raw data, cluster
and classify it, and over time continuously
learn and improve.

2. ANN is replica of neuron system in human brain.
The brain composed of billions neuron which are
interconnected each others. A biological neuron
consists of three main elements,
• Dendrites: That are input signal channel which
the strength of connections to nucleus are
affected by weights.
• Cell Body: Where computation of input signal and
weights generate output signal which will be
delivered to another neurons.
• Axon: Is part which transmit output signal to
another neurons that are connected to it.

3. Biological Neural Network Artificial Neural Network
Dendrites Inputs
Cell Nucleus Nodes
Synapse Weights
Axon Output

5.  Input Layer.
 Hidden Layer.
 Output Layer.

6.  in terms of the human brain, these input signals
are your senses. These senses are whatever you
can see, hear, smells, or touch. For example, if
you touch some hot surface, then suddenly a
signal sent to your brain. And that signal is the
Input signal in terms of the human brain.
 In terms of an artificial neural network, the input
layer contains independent variables. So the
independent variable 1, independent variable 2,
and independent variable n.

7. Inside the neurons, the two main important steps happen-
Weighted Sum.
Activation Function.
 The first step is the weighted sum, which means all of the
weights assigned to the synapses are added with input
values. Something like that-
[ x1.w1+x2.w2+x3.w3+………………..Xn.Wn]
 After calculating the weighted sum, the activation function is
applied to this weighted sum. And then the neuron decides
whether to send this signal to the next layer or not.
 I hope now you understood the basic work procedure of an
Artificial Neural Network. Now let’s move to the
implementation of Artificial Neural Network in Python.

8. The answer is the output value can be-
 Continous( Like price).
 Binary( in Yes/no form).
 Categorical variable.

9.  Artificial Neural Networks can be viewed as weighted
directed graphs in which artificial neurons are nodes,
and directed edges with weights are connections
between neuron outputs and neuron inputs.
 The Artificial Neural Network receives information
from the external world in pattern and image in
vector form. These inputs are designated by the
notation x(n) for n number of inputs.
 Each input is multiplied by its corresponding weights.
Weights are the information used by the neural
network to solve a problem. Typically weight
represents the strength of the interconnection
between neurons inside the Neural Network.

10.  The weighted inputs are all summed up inside
the computing unit (artificial neuron). In case the
weighted sum is zero, bias is added to make the
output not- zero or to scale up the system
response. Bias has the weight and input always
equal to ‘1'.
 The sum corresponds to any numerical value
ranging from 0 to infinity. To limit the response
to arrive at the desired value, the threshold value
is set up. For this, the sum is forward through an
activation function.
 The activation function is set to the transfer
function to get the desired output. There are
linear as well as the nonlinear activation function.

11. Some of the commonly used activation function
is - binary, sigmoidal (linear) and tan hyperbolic
sigmoidal functions(nonlinear).
 Binary - The output has only two values, either 0
and 1. For this, the threshold value is set up. If
the net weighted input is greater than 1, the
output is assumed as one otherwise zero.
 Sigmoidal Hyperbolic - This function has an ‘S’
shaped curve. Here the tan hyperbolic function is
used to approximate output from net input. The
function is defined as - f (x) = (1/1+ exp(-????x))
where ???? - steepness parameter.

12. Supervised Learning:
In this learning, the training data is input to
the network, and the desired output is known
weights are adjusted until production yields
desired value.
Unsupervised Learning:
Use the input data to train the network
whose output is known. The network
classifies the input data and adjusts the
weight by feature extraction in input data.

13. Reinforcement Learning:
Here, the output value is unknown, but the
network provides feedback on whether the
output is right or wrong. It is Semi-Supervised
Learning.
Offline Learning:
The weight vector adjustment and threshold
adjustment are made only after the training set is
shown to the network. It is also called Batch
Learning.
Online Learning:
The adjustment of the weight and threshold
is made after presenting each training sample to
the network.

14. The Implementation of an Artificial Neural
Network in Python is Data Preprocessing. The
steps are,
1. Import the Libraries
2. Load the Dataset
3. Split Dataset into X and Y
4. Encode Categorical Data
5. Split the X and Y Dataset into the Training
set and Test set
6. Perform Feature Scaling

15. Neural Networks are regulating some key sectors
including finance, healthcare, and automotive. As
these artificial neurons function in a way similar to
the human brain. They can be used for image
recognition, character recognition and stock market
predictions.

16.  Neural networks are suitable for predicting time
series mainly because of learning only from
examples, without any need to add additional
information that can bring more confusion
than prediction effect. Neural networks are able
to generalize and are resistant to noise.