The document discusses neural networks, including feed-forward and feedback neural networks. It defines neural networks as computer systems modeled after the human brain. It describes the key components of neural networks as input, processing, and output layers. It differentiates between feed-forward neural networks where signals only travel one way and feedback neural networks where signals can travel in both directions. The document also covers learning strategies, applications, advantages, and disadvantages of neural networks.
Heart Disease Prediction using machine learning.pptx
DATA SCIENCE
1. School of Computing Science and Engineering
Course Code: BTCS9212 Course Name: Data Sciences
CAT 3 EXAMINATION
TOPIC
NEURAL NETWORK: FEED-FORWARD AND FEEDBACK LOOP
Elective Section- 5
Group-11
TEAM DETAILS-
1. Harshika Bansal(20SCSE1010558)
2. Harshit Gupta(20SCSE1010585)
3. Hemant Kumar Sahani(20SCSE1010542)
SUBMITTED TO:-
Dr. S. Janarthanan
Program Name: B.Tech (CSE)
2. NEURAL NETWORK
• A neural network is a computer system modeled on the human brain and nervous
system.
• Neural Network is an information processing sample based on the working of
biological nervous systems to process information. It is like the human brain. In this
sense, neural networks refer to systems of neurons, either organic or artificial in
nature.
• A neural network works similarly to the human brain’s neural network. A “neuron” in
a neural network is a mathematical function that collects and classifies information
according to a specific architecture.
• The network bears a strong resemblance to statistical methods such as curve fitting and
regression analysis.
Program Name: B.Tech (CSE)
3. COMPONENTS OF A NEURAL NETWORK
There are three main components:
• an input layer
• a processing layer
• an output layer
The inputs may be weighted based on various criteria. Within the processing
layer, which is hidden from view, there are nodes and connections between
these nodes, meant to be analogous to the neurons and synapses in an animal
brain.
Program Name: B.Tech (CSE)
4. TYPES OF NEURAL NETWORKS
1. FEED FORWARD NEURAL NETWORK
Signals travel in one way i.e. from input to output only in Feed
forward Neural Network. There is no feedback or loops. The output
of any layer does not affect that same layer in such networks. Feed
forward neural networks are straight forward networks that associate
inputs with outputs. They have fixed inputs and outputs. They are
mostly used in pattern generation, pattern recognition and
classification.
Program Name: B.Tech (CSE)
5. TYPES OF NEURAL NETWORKS
2. FEEDBACK NEURAL NETWORK
• Signals can travel in both directions in Feedback neural
networks.
• Feedback neural networks are very powerful and can get
very complicated. They are dynamic. Computations derived
from earlier input are fed back into the network, which
gives them a kind of memory.
• Feedback networks are dynamic; their 'state' is changing
continuously until they reach an equilibrium point. They
remain at the equilibrium point until the input changes and
a new equilibrium needs to be found.
Program Name: B.Tech (CSE)
6. LEARNING STRATEGIES FOR NEURAL NETWORK
1. SUPERVISED LEARNING:
In this type of machine learning training, the dataset contains input data and the value
you want to predict. The ANN will use the training data to learn a link between the input
and the outputs. The idea behind this is that the training data can be generalized and that
the ANN can be used on new data with some accuracy.
Pattern recognition is one of the best examples of such learning.
2. UNSUPERVISED LEARNING:
This type of learning is required when there is no example data set with known answers.
For example, searching for a hidden pattern. In this case, clustering i.e., dividing a set of
elements into groups according to some unknown pattern is carried out based on the
existing data sets present.
Program Name: B.Tech (CSE)
7. APPLICATION OF NEURAL NETWORKS
• Signal Processing-
Neural networks can be trained to process an audio signal and filter it appropriately
in the hearing aids.
• Medical-
Cancer cell analysis, EEG and ECG analysis, prosthetic design, transplant time
optimizer
• Aerospace-
Autopilot aircraft, aircraft fault detection
• Software-
Pattern Recognition in facial recognition, optical character recognition, etc…
Program Name: B.Tech (CSE)
8. ADVANTAGES OF NEURAL NETWORK
• A neural network can perform tasks that a linear program can not.
• When an element of the neural network fails, its parallel nature can
continue without any problem.
• A neural network learns, and reprogramming is not necessary.
• It can be implemented in any application.
• It can be performed without any problem
Program Name: B.Tech (CSE)
9. DISADVANTAGES OF NEURAL NETWORK
• The neural network needs training to operate.
• The architecture of a neural network is different from the architecture of
microprocessors. Therefore, emulation is necessary.
• Requires high processing time for large neural networks.
Program Name: B.Tech (CSE)
10. CONCLUSION
• 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 the prediction effect.
• The neural network can generalize and are resistant to noise.
• For more complex nonlinear relations between input and output, larger training
datasets were found to be more successful
Program Name: B.Tech (CSE)