NeuralNetw08022024124214 0

Neural Network
WHAT
HOW
TECHNOLOGY
Lets Recap
Artificial Intelligence:
1. Artificial Intelligence refers to any technique that enables computers to mimic human
intelligence.
2. AI-enabled machines think algorithmically and execute what they have been asked for
intelligently.
3. A machine will automatically mimic human intelligence.
Machine Learning:
1. Machine Learning enables machines to improve at tasks with experience.
2. The machine learns from its mistakes and takes them into consideration. It improvises using its
own experiences.
3. If a Machine can improvise it is at par with Human Intelligence.
Lets Recap
Deep Learning:
1. Deep Learning enables software to train itself to perform tasks with vast amounts of data.
2. Machines with Deep Learning are intelligent enough to develop algorithms for themselves.
3. In deep learning, the machine is trained with huge amounts of data which helps it to train itself
around the data. Such machines are intelligent enough to develop algorithms for themselves
Most advanced form of Artificial Intelligence is:

1. Deep Learning is the most advanced form of Artificial Intelligence.
2. Artificial Intelligence covers all the concepts and algorithms which, in some way or the other
mimic human intelligence.
3. Machine learning is the most advanced form of Artificial Intelligence.
Lets Recap
Decision Trees:
1. All data holds importance while developing the Decision Tree.
2. The beginning point of any Decision Tree is known as its Root.
3. Decision Trees is a rule-based AI model which helps the machine in predicting what an element is
with the help of various rules.
Getting Started
Types of AI Models
Rule based Approach:
• Under Rule based approach, the developer feeds in data along with some ground rules to the
model. The model gets trained with these inputs and gives out answers in the form of
predictions. This approach is commonly used when we have a known dataset or labelled dataset.
Getting Started
Types of AI Models
Learning based Approach:
• the Machine Learning approach the developer feeds in data along with the answers. The machine
then designs its own algorithms and methodologies to match the data with answers and gives out
the rules. This approach is commonly used when the data is unknown/random or unlabelled.
What is Neural Network
 known as Artificial Neural Network
•Decision Maker
 It is also a functional Unit of Deep learning
•Subset of Machine Learning
•Subset of AI
 Mimics Human brain to solve complex data
driven programs
 Used to recognize patterns & predict
output
https://www.youtube.com/watch?v=g08A2wiqlxA
Neural Network
 Neural networks are loosely modelled after how neurons in the
human brain behave.
 The key advantage of neural networks, are that they are able to
extract data features automatically without needing the input of the
programmer.
 A neural network is essentially a system of organizing machine
learning algorithms to perform certain tasks.
 It is a fast and efficient way to solve problems for which the dataset
is very large, such as in images.
History of Neural Network
 Neural networks were first proposed in 1944 by

Warren Mcculloch and Walter Pitts.
 Origins - Algorithm that's try to mimic the human mind.
 Was very widely used in early 80s and early 90s.
 Popularity diminished in late 90s due to hardware
limitations.
How Neural Network Works
How Neural Network Works
Why Neural Networks
Why Neural Network Needed
• The main objective is to develop a system to perform
various computational tasks faster than the traditional
systems.
• Based on working of Human Brain
• Helps us to work towards AI
• More efficient in forecasting and classification
Features of Neural Network
Neural network system are modelled on the human brain and nervous
system.
They are able to automatically extract feature without input from the
programmer.
Every neural network node is essentially a machine learning algorithm.
It is useful when solving problem for which the data set is very large.
Neural Network in Every Day Life
Pattern recognition &
Decision Making
 Real Time Translation
(Google Translation)
 Radars
 Facial Recognition
 Medical Science
 Automated Driving Vehicles
 Handwriting Recognition(pen
to Print)
How Human Brain Works
https://www.youtube.com/watch?v=6qS83wD29PY
How Human Brain Works
How ANN Works
Axon
Axon Terminal
Dendrite
Nucleus
Similarity b/w NN and ANN
What is ANN
What is ANN
Neurons
What is ANN
Bias: Each Activation function
neuron has some
value
Connectors
Amplitude: Value
of letter that we Weight: Value of
are speaking connectors
What is ANN
Backward propagation
Forward propagation
Important Terms Learnt
Neurons Bias Forward Propagation
Input Layer weight Backward Propagation
Output Layer Activation function ANN
Hidden Layer connectors
https://poloclub.github.io/cnn-explainer/
Activities
• https://code.org/ai
• www.Kipwing.com/cartoonify
• www.quickdraw.com
• www.distill.pub/2016/handwriting/
• www.magenta.tensorflow.org/assets/sketch_rnn_demo/multi_predic
t.html
• https://poloclub.github.io/cnn-explainer/
What is ANN
 Artificial Neural Network are programs design to solve any problem by trying to mimic the
structure and the function of a nervous system
 Neural Networks are based on simulated neurons, which are joined together in a variety of
ways to form networks.
 Neural Network resembles the human brain in two ways:
 It acquires knowledge through learning

 Its knowledge is stored within the inter connection strengths known as synaptic weight
https://www.youtube.com/watch?v=bfmFfD2RIcg&t=116s

NeuralNetw08022024124214 0

Uploaded by

Copyright:

Available Formats

NeuralNetw08022024124214 0

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

NeuralNetw08022024124214 0

Uploaded by

Copyright:

Available Formats

Neural Network

Most advanced form of Artificial Intelligence is:

 Neural networks were first proposed in 1944 by

Every neural network node is essentially a machine learning algorithm.

Input Layer weight Backward Propagation

Output Layer Activation function ANN

Hidden Layer connectors

 It acquires knowledge through learning

You might also like