Scribd
Upload
11 views3 pages

Workshop2 - BioInformatics

Uploaded by

gmi.tn.dev.ksenthil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
11 views3 pages

Workshop2 - BioInformatics

Uploaded by

gmi.tn.dev.ksenthil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Workshop - BioInformatics

DAY 2

Artificial Neural Network


● Artificial neural network is a computer model inspired by the brain's
structure.
● Its key component of deep learning.
● Artificial neurons are software modules called nodes and artificial neural
networks are software programs or algorithms to solve problems.

Architecture:
Input layer →hidden layer → output layer

Input Layer : It picks up the input signal and passes them to be the next
layer.
Hidden Layer : Hidden layer analyzes the output from the previous layer,
processes it further and passes it to the next layer.
Output Layer : The output layer gives the final result of all the data
processing by the artificial neural network.

Feedforward neural networks:


Feedforward neural networks process data in one direction, from the input
node to the output node.
Back Propagations :
Back propagation is the process of updating the weight of the network in
order to reduce the error in prediction.

Convolutional Neural Network.


● Convolutional Neural Networks are widely used in image recognition,
classification, and object detection.
● It's a complex image.
● CNNs use convolutional layers as building blocks.
● These layers apply a set of filters to the input data. It detects specific
features in the input, such as edges, textures, or patterns.

Linear regression:
● Linear regression analysis is used to predict the value of a variable based
on the dataset .
● The variable which we are going to predict is called the dependent
variable.

Activated function:
A single neuron will fire ,or activate when it thinks it has something worth
communicating to the other neurons connected to it.

Types of activated function :


1) Threshold: A threshold value determines whether a neuron should be
activated or not activated in a binary step activation function.
2) Relu function: Return Zero when the input value is less than zero and
otherwise it returns the same value.
3)sigmoid function: return the out in binary value.

Hyperparameters :
Hyperparameter tuning is the process of selecting the optimal values for a
machine learning model’s hyperparameters.
Hyperparameters are settings that control the learning process of the
model, such as the learning rate, the number of neurons in a neural
network, or the kernel size in a support vector machine.

Convolution Layer :
The convolutional layer is the core building block of a CNN, and it is where
the majority of computation occurs. It requires a few components, which
are input data, a filter, and a feature map.
Dataset-Kaggle

Task :
Predicted the Diabetes Prediction whether a person has diabetes or not.
Steps :
1. First imported the libraries and loaded the dataset.
2. Exploring the dataset.
3. Data Cleaning.
4. Train and test the data.

You might also like