Our Eyes act as an
Input Unit to send
message to our brain.
Our sense organs behave as input
layer of our body.
Message travelled through a
neuron to reach our brain.
Human brain process that
message and instruct an
appropriate action(Output) to be
taken by other body parts.
Multiple Hidden Layers
Input Layer Of Neuron
Hidden Layers
Processing
Output Layer
Artificial Neural Networks
•Biologically motivated approach to machine learning.
•Fundamental processing elements of a neural network is a
neuron.
•In technical systems, we also refer to them as units or
nodes.
•Also known as Artificial Neural Network (ANN).
•Information is transmitted as a series of electric impulses,
so-called spikes.
Neural Networks
What is a Neural Network?
•A neural network is a system of organizing machine
learning algorithms to perform certain tasks. It is a fast and
efficient way to solve problems for which the data set is
very large .
•Neural networks are loosely modelled after how neurons
in the human brain behave.
•The key advantage of neural networks is that they are able
to extract data features automatically without needing the
input of the programmer
How do our brains work?
▪ The Brain is a massively parallel information
processing system.
▪ Our brains are a huge network of processing
elements. A typical brain contains a network
of 10 billion neurons.
How do our brains work?
▪ A processing element
Dendrites: Input Cell body: Processor
Synaptic: Link Axon: Output
How do our brains work?
• A neuron is connected to other neurons through
about 10,000 synapses.
• A neuron receives input from other neurons.
Inputs are combined.
• Once input exceeds a critical level, the neuron
discharges a spike ‐ an electrical pulse that
travels from the body, down the axon, to the
next neuron(s).
• The axon endings almost touch the dendrites or
cell body of the next neuron.
• This link is called a synapse. The strength of the
signal that reaches the next neuron.
How do ANNs work?
An artificial neuron is an imitation of a human neuron
How do ANNs work?
Artificial Neural Networks
• A Neural Network is divided into multiple layers and
each layer is further divided into several blocks called
nodes.
• The first layer of a Neural Network is known as the
input layer. The job of an input layer is to acquire data
and feed it to the Neural Network. No processing
occurs at the input layer.
• Next to it are the hidden layers. Hidden layers are those
layers where the whole processing occurs.
• Each node of these hidden layers has its own machine
learning algorithm which it executes on the data
received from the input layer.
Artificial Neural Networks
• The processed output is then fed into the subsequent
hidden layer of the network.
• There can be multiple hidden layers in a neural network
system and their number depends on the complexity
of the function for which the network has been
configured.
• The last hidden layer passes the final processed data to
the output layer, which then gives it to the user as the
final output.
• Similar to the input layer, output layer too does not
process data which it acquires. It is meant for user
interface.
How do ANNs work?
How do ANNs work?
• Now, let us have a look at the model of an artificial neuron.
Neural Network is a set of connected INPUT/OUTPUT UNITS,
where each connection has a WEIGHT associated with it.
How do ANNs work?
............
Input xm x2 x1
Processing ∑
∑= X1+X2 + ….+Xm =y
Output y
Neural Network
• The terms “neural networks” and “deep learning” are
often used interchangeably, although they are distinct
from each other.
• With deep learning, the computer continually trains itself
to process data, learn from it, and build more
capabilities. The multiple layers of more complex
artificial neural networks make this possible.
• Neural Networks are trained typically in three ways:-
Supervised learning
Unsupervised Learning
Reinforcement learning
Supervised Learning
• Supervised learning, also known
as supervised machine learning, is
defined by its use of labeled
datasets to train algorithms that
to classify data or predict
outcomes accurately.
• This relationship is represented by
the values of the weights of the
trained network.
Supervised Learning
Examples of Supervised Learning
•Image- and object-recognition: Used to locate, isolate, and
categorize objects out of videos or images
•Predictive analytics: Creating predictive analytics systems to provide
deep insights into various data points. This allows enterprises to
anticipate certain results.
•Customer sentiment analysis: Using supervised machine learning
algorithms, organizations can extract and classify important pieces of
information from large volumes of data—including context, emotion,
and intent. This can be incredibly useful when gaining a better
understanding of customer interactions and can be used to improve
brand engagement efforts.
•Spam detection: Organizations can train databases to recognize
patterns or anomalies in new data to organize spam and non-spam-
related correspondences effectively.
Supervised Learning Algorithms
Classification uses an algorithm to accurately assign test
data into specific categories. It recognizes specific entities
within the dataset and attempts to draw some conclusions.
Here data is classified according to labels.
Common classification algorithms are :-
• Linear classifiers
• Decision trees
• K-nearest neighbor
• Random forest
• Support vector
machines (SVM
Supervised Learning Algorithms
Regression Algorithms predict the output values based on
input features from the data fed in the system. It is commonly
used to make projections, such as for sales revenue for a
given business. Such algorithm work on continuous data.
Types of regression algorithms are: -
• Linear
regression
• Logistical
regression
• Polynomial
regression.
Unsupervised Learning
• Unsupervised learning, also
known as unsupervised machine
learning, uses machine learning
algorithms to analyze and
cluster unlabeled datasets.
• These algorithms discover
hidden patterns or data
groupings without the need for
human intervention.
• Faster than supervised learning.
Unsupervised Learning Algorithms
The unsupervised learning algorithm can be further
categorized into two types :-
• 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.
Unsupervised Learning Algorithms
Association: 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.
For example
• People that buy a new home most likely to buy new
furniture.
• Groups of shopper based on their browsing and
purchasing histories.
• Movie group by the rating given by movies viewers
Reinforcement Learning
Reinforcement Learning is a
part of machine learning.
Here, networks are self-trained
on reward and punishment
mechanisms.
It’s about taking the best
possible action or path to gain
maximum rewards and
minimum punishment through
observations in a specific
situation.
Advantages of Neural Networks Over
Conventional Techniques
• Neural networks can be expected to self-train quite
efficiently in case of problems where the relationships
are dynamic or nonlinear.
• Neural networks are an analytical alternative to serial
system where steps are deterministic, sequential and
logical.
• The ability of neural networks to examine a variety of
relationships makes it easier for the user to quickly
model phenomena that may have been quite difficult,
or even impossible, to comprehend otherwise.
Applications
• Handwritten Digit Recognition
• Face recognition
• Time series prediction
• Process identification
• Process control
• Optical character recognition
• Forecasting/Market Prediction: finance and banking
• Manufacturing: quality control, fault diagnosis
• Medicine: analysis of electrocardiogram data, RNA &
DNA sequencing, drug development without animal
testing
[Link] (A): A Neural Network helps in building predictive models based on huge data
sets.
Reason (R): Backpropagation is one of the techniques used to train an Artificial Neural
Network.
(i) Both A and R are correct and R is the correct explanation of A.
(ii) Both A and R are correct but R is NOT the correct explanation of A.
(iii) A is correct but R is incorrect.
(iv) A is incorrect but R is correct
[Link] which type of neural network training, the networks are trained to provide
correct output by using several example inputs?
a. Supervised Learning b. Unsupervised Learning
c. Reinforcement Learning d. None of the above
3. Neural networks are said to be modelled the way how neurons in the human brain behave.
A similar system is mimicked by the AI machine to perform certain tasks. Explain how neural
networks work in an AI model and mention any three features of Neural Networks.
4. A _______________is divided into multiple layers and each layer is further divided into
several blocks called nodes.
a. Neural Networks b. Convolutional Neural Network (CNN)
c. Machine learning algorithm d. Hidden Layers