Scribd
Upload
2 views

Feed forward neural network presentation of sami and daim

Uploaded by

97 Haseeb
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views

Feed forward neural network presentation of sami and daim

Uploaded by

97 Haseeb
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

FEED FORWARD NEURAL NETWORK

SAMIULLAH RAFIQUE F21-0572


DAIM ZIA QAZI F21-0544
FEED FORWARD NEURAL NETWORK:
• A Feedforward Neural Network (FNN) is a type of artificial neural
network where the data flows only in one direction, from input layer to
output layer, without any feedback loops .
• No loops or cycles exist in this network
• A single layer feed forward network has one layer of nodes, whereas a
multilayer feed forward network has multiple layers of nodes.
ARCHITECTURE:
1. Input Layer:
Takes in features of the dataset (e.g., images, text,
numerical data). Hidden Layers:
One or more layers that process the input data.Higher the
number of hidden layers higher will be the accuracy of output
3. Output Layer:
Produces predictions or outputs (e.g., class probabilities,
regression values).
DIAGRAM:
CHARACTERISTICS:
1. Unidirectional Data Flow:
Data flows from input layer to output layer.
2. No Feedback Loops:
No connections from later layers to earlier layers.
3. No Recurrent Connections:

No connections from a layer to


itself.
HOW FNNS WORK:
1. Forward Propagation:
Input data flows through the network, layer by layer.
2. Activation Functions:
Each node (neuron) applies an activation function to the
weighted sum of inputs. Add non-linearity to help the model learn complex
patterns (e.g., ReLU, sigmoid, tanh)
3. Output:
The final output is produced by the output layer.
ADVANTAGES:
1.Easy to Implement:
FNNs are relatively simple to design and train.
2. Fast Computation:
FNNs can process information quickly.
3. Universal Approximation:
FNNs can approximate any continuous function.
4.Versatility:
Can handle various data types (numerical, categorical, image, etc.)
PYTHON CODE FOR FNN:
THANK YOU

You might also like