You are on page 1of 8

Prepared By:

2021-ME-108(SDP)
2021-ME-139(SDP)
Contents
NEURAL NETWORKS

TYPES OF NEURAL NETWORKS

A C T I VAT I O N F U N C T I O N S A N D
TYPES
Artificial Neural Networks (ANN)

• Artificial Neural Networks (ANNs) are machine


learning models inspired by the human brain's
structure and function.
• ANNs consist of interconnected nodes (neurons)
that process information similarly to human
neurons.
• Their primary purpose is to learn from data and
improve their performance through training.
• ANNs find applicati ons in various fields,
including image recognition, speech recognition,
and natural language processing.

Reference: Introduction to Artificial Neural Networks - Analytics Vidhya. (n.d.). Retrieved


September 20, 2023, from https://www.analyticsvidhya.com/blog/2021/09/introduction-
to-artificial-neural-networks/
Architecture of Artificial Neural
Networks
• ANNs (Artificial Neural Networks) are organized into layers,
typically including an input layer, one or more hidden layers, and
an output layer.
• Neurons within each layer are connected to neurons in adjacent
layers through weighted connections.

Input Layer:
• First layer that receives raw input data.
• Neurons in this layer represent individual features or inputs.
Hidden Layers:
• Intermediate layers between input and output layers.
• Neurons in these layers perform computations and feature
transformations.
Output Layer:
• The final layer produces the network's output.
• The activation function in this layer depends on the task

Reference: Introduction to Artificial Neural Networks - Analytics Vidhya. (n.d.). Retrieved September 20, 2023, from
https://www.analyticsvidhya.com/blog/2021/09/introduction-to-artificial-neural-networks/
Types of Artificial Neural Network
There are many types of artificial neural Network but some common are:-

1. Feedforward Neural Network


Feedforward Neural Networks (FNNs) are the simplest type of ANNs. They consist of an input layer, one or more
hidden layers, and an output layer. They are widely used in image and speech recognition systems.

2. Recurrent Neural Network

They have feedback connections that allow information to be passed between previous and current steps. RNNs
are suitable for tasks like language modelling, speech recognition, and time series analysis.

3. Convolutional Neural Network


Convolutional Neural Networks (CNNs) are highly effective in analysing grid-like data, such as images or time
series. Their ability to capture local patterns makes them indispensable in deep learning.
Activation Functions
◦ An Activation Function decides whether a neuron should be activated or not.

◦ Activation functions introduce non-linearity to neural networks.

◦ They help neurons learn complex patterns and relationships in data.

◦ Activation functions decide whether a neuron should "fire" or not based on input.

◦ They introduce thresholds, enabling neural networks to model complex functions.

◦ Common activation functions include ReLU, Sigmoid, and Tanh.


Types of
Activation
Functions

You might also like