Ai Unit 7

UNIT-3
Neural Networks
Learning Objectives:
1. Working of neural network
2. Single layer Neural Network
3. Neural Network Vs Human Nervous System
4. How do Neural Network learn?
5. Deep Learning and Machine learning comparison
6. Applications of Deep Learning
Neural Network: A Neural Network is either a system software of hardware that

works similar to the task performed by neurons of human brain.
Neural Network (better known as Artificial neural networks or ANN) is one of the
main tools used in machine learning.
As the “neural” part of their name suggests they are brain -inspired system which
are intended to replicate the way that we humans learn.
Basics of Neural Networks: It includes the three layers as given below.
• Input Layer: Corresponds to Dendrites (a short-branched extension of a nerve

cell) in a neuron
• Hidden Layer: Feature Extraction is done here (Information processing
happens here)
• Output Layer: Corresponds to Axon (a nerve cell along which impulses are
conducted from the cell body to other cells.) in a neuron.
Biological Neural Network Artificial Neural Network

Soma Node
Dendrites Input
Synapse Weights or interconnections
Axon Output
Neural Network Vs Human Nervous System:

Your brain is made of approximately 100 billion nerve cells, called neurons.
Neurons are specialised to transmit information throughout the body. These
highly specialised nerve cells are responsible for communicating information in
both chemical and electrical forms.
They can transmit signals over long distances (up to several feet or a few
meters) and send messages to each other.
Algorithm
An algorithm is a set of instructions used in machine learning that allows a

computer programme to mimic how a human learns to classify certain types of
data.
a. Supervised Learning
Supervised learning is a method of developing artificial intelligence that involves training a

computer algorithm on input data that has been labeled for a certain output.
Example of Supervised Learning

You obtain a set of photographs with descriptions of what’s on them, and then you train a
model to detect fresh photos.
b. Unsupervised Learning
The use of artificial intelligence (AI) systems to find patterns in data sets including data points
that are neither categorized nor labeled is known as unsupervised learning.
Example of Unsupervised Learning

Assume the unsupervised learning algorithm is given an input dataset with photographs of
various cats and dogs. The algorithm is never trained on the given dataset, therefore it has no
knowledge what the dataset’s characteristics are.
c. Reinforcement Learning
“An intelligent agent interacts with the environment and learns to operate within that
environment through reinforcement learning.”
Example of Reinforcement Learning
Neural Network
Warren McCulloch and Walter Pitts proposed neural networks for the first time in 1944.
A neural network is an artificial intelligence strategy for teaching computers to analyze data in
the same way that the human brain does. Deep learning is a form of machine learning technique
that employs interconnected nodes or neurons in a layered structure to mimic the human brain.
It develops an adaptive framework that allows computers to learn from their errors and
continuously improve.
Some of the features of a Neural Network are listed below:
1. The human brain and nervous system are used to model neural network systems.
2. They can automatically extract features without the programmer’s input.
3. Every node in a neural network is a machine learning algorithm.
4. It comes in handy while working on difficulties with a large data set.
Neural Networks Vs Human Nervous System
In the subject of Neural Network research, the biological brain and Artificial Neural Networks
are two of the most challenging areas of study.
a. SIZE: The human brain contains 86 billion neurons and over 100 trillion connections that
transmit electrical information throughout the body. The number of neurons in the artificial
neural network is far lower.
b. MEMORY: The primary distinction is that humans forget, whereas neural networks do not.
A neural network that has been properly trained.
c. ENERGY CONSUMPTION: The biological brain uses roughly 20% of the total energy
consumed by the human body. Artificial constructions can’t even come close to matching the
efficiency level of a biological brain, which operates on roughly 20 watts.
Exercise 4.0
MCQs:
1. Choose the option that is not a type of learning from the list below.
a. Supervised Learning b. Unsupervised Learning
c. Reinforcement Learning d. None of the above
2. Identify the type of “facial identities for facial expressions” learning algorithm.
a. General patterns b. Unsupervised patterns
c. Recognition patterns d. None of the above
3. What is the term for applying machine learning techniques to a large database?
a. Data encapsulation b. Database
c. Data mining d. None of the above
4. Determine the type of learning that uses labelled training data.

c. Reinforcement Learning d. All of the above
5. What is the word for the process through which machine learning algorithms
construct a model from sample data?
a. Transfer data b. Data training
c. Training data d. All of the above
6. Which of the following is a subset of machine learning?

a. Artificial Intelligence b. Data Learning c.
c. Deep Learning d. All of the above
7. What are the various types of learning algorithms?

8. A approach of building artificial intelligence that involves training a computer

algorithm on input data that has been tagged for a specific output is known as
______________.
9. The use of Artificial Intelligence (AI) systems to detect patterns in data sets that
aren’t categorized or labelled is referred to as _______________.
10. An intelligent agent interacts with the environment and learns to operate within that
environment through ____________
11. A __________ is an artificial intelligence strategy for teaching computers to analyze
data in the same way that the human brain does.
a. Neural Network b. Cell Network
c. Brain Network d. None of the above
12. What are the features of a Neural Network?

a. The human brain and nervous system are used to model neural network systems.
b. They can automatically extract features without the programmer’s input.
c. Every node in a neural network is a machine learning algorithm.
d. All of the above
Short Answer Type Questions
1. What is algorithm?
Answer – A machine learning algorithm is a series of instructions that allows a computer
programme to replicate how a human learns to classify different types of data.
2. Type of learning algorithm?

Answer – There are three type of learning algorithm.
a. Supervised Learning
b. Unsupervised Learning
c. Reinforcement Learning
3. What is supervised learning?

Answer – Supervised learning is a method of artificial intelligence development that involves
training a computer algorithm on labelled input data for a specific output.
4. What is unsupervised learning?

Answer – Unsupervised learning is the use of artificial intelligence (AI) systems to detect
patterns in data sets that contain data points that are neither categorized nor labelled.
5. What is reinforcement learning?

Answer – Through reinforcement learning, an intelligent agent interacts with the
environment and learns to operate within it.
6. What are the future of Neural network?

Answer – The future of Neural network are –
a. Neural network systems are modelled using the human brain and nervous system.
b. They can extract features without the input of the programmer.
c. A neural network’s nodes are all machine learning algorithms.
d. It comes in handy when dealing with problems involving a huge data set.

Ai Unit 7

Uploaded by

Copyright:

Available Formats

Ai Unit 7

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Ai Unit 7

Uploaded by

Copyright:

Available Formats

UNIT-3

Neural Network: A Neural Network is either a system software of hardware that

Basics of Neural Networks: It includes the three layers as given below.

• Input Layer: Corresponds to Dendrites (a short-branched extension of a nerve

Biological Neural Network Artificial Neural Network

Neural Network Vs Human Nervous System:

An algorithm is a set of instructions used in machine learning that allows a

Supervised learning is a method of developing artificial intelligence that involves training a

Example of Supervised Learning

Example of Unsupervised Learning

Example of Reinforcement Learning

Some of the features of a Neural Network are listed below:

Neural Networks Vs Human Nervous System

4. Determine the type of learning that uses labelled training data.

6. Which of the following is a subset of machine learning?

7. What are the various types of learning algorithms?

8. A approach of building artificial intelligence that involves training a computer

12. What are the features of a Neural Network?

Short Answer Type Questions

2. Type of learning algorithm?

3. What is supervised learning?

4. What is unsupervised learning?

5. What is reinforcement learning?

6. What are the future of Neural network?

You might also like