[go: up one dir, main page]
Scribd
Upload
7 views7 pages

Vinitha - Workshop-Bioinformatics

Uploaded by

gmi.tn.dev.vanbazhagan
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
7 views7 pages

Vinitha - Workshop-Bioinformatics

Uploaded by

gmi.tn.dev.vanbazhagan
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/ 7

BIOINFORMATICS WORKSHOP

Artificial intelligence:

AI is use in the magical wand to create the incredible things.Ai is like the
human intelligence and slove the problem Easily.

Introduction to machine learning:

⦁ Machine learing is making a computer to learn and act like a


humans by feeding the data and information.

⦁ Machine learing is Algorithm based that means algorithm is a set of


commands that must be followed for a computer to perform
calculations or other problem-solving operations.

Introduction to Deep learning:

⦁ Deep learning is more data will be insert in to the computer and it


will be accurate value to provide.

⦁ Deep learing is architecture based

Popular AI :
ChatGpt :

⦁ It is use for the human give the some of instruction of Ai it will be


provide the various type of out put.

Hologram;

⦁ 3D view for example the person can not speak in tamil the hologarm
ai is help into convert in to tamil language in that kind of person
image in 3D view can be display.

1
Python:

Data Structure:

List: collection of object is called the List it is represented by [] . the List is


can be change it is a mutable.

tuple: it also collection of object it is represented by().tuple is can not be


change it is a immutable.

Set: Collection of non duplicate elements.it is represented {}

Dictionary: key and value

Build in function in python:

Length: len() function returns the number of characters in the string

concatenation: to join the to datatype.

membership: return the boolean value

append: value are add into the list

multiple value can be add you can use in extend function.

split: split() function can be use in split the line in one by one.

Task:

Uploaded the data and plot the value between skin thickness,BMI and
Age

import matplotlib.pyplot as plt

import numpy as np

2
import seaborn as sns

dataframe = pd.read_csv("/content/machine_learning/kaggle_diabetes.csv")

print(dataframe.head())

ax = sns.scatterplot(x="SkinThickness",
y="BMI",hue="Age",data=dataframe)

plt.show()

Pregnancies Glucose BloodPressure SkinThickness Insulin BMI

0 2 138 62 35 0 33.6

1 0 84 82 31 125 38.2

2 0 145 0 0 0 44.2

3 0 135 68 42 250 42.3

4 1 139 62 41 480 40.7

Diabetes PedigreeFunction Age Outcome

0 0.127 47 1

1 0.233 23 0

2 0.630 31 1

3 0.365 24 1

4 0.536 21 0

3
Neural network:

⦁ Neural networks can help computers make intelligent decisions


with limited human assistance because they can learn and model the
relationships between input and output data .

⦁ that means the defferent types of data you can insert it and its call
the input data it is a 1st layer of Neural network. and input layer
throw the data in to the second layer of hidden layer . the hidden layer
evaluate the data and pass into the output layer.

4
coding part:

from keras.models import Sequential

from keras.layers import Dense

import numpy

X = dataset[:,0:8] // input data

Y = dataset[:,8]

create model:

model = Sequential()

model.add(Dense(12, input_dim=8, activation='relu')) // 1st input layer

model.add(Dense(8, activation='relu')) // hidden layer

model.add(Dense(1, activation='sigmoid')) // output layer

comile model:

model.compile(loss='binary_crossentropy', optimizer='adam',
metrics=['accuracy']) // loss function is use in iteration the data throw the
error until the error can be 0 they give the output for accuracy value.

Fit the Model:

model.fit(X, Y, epochs=200, batch_size=10) // epochs means how many


times the data will be iteration

5
Activated function:
A single neural will fire ,or activate when it thinks it has somthing worth
communicating to the other neurons connected to it.

Types:

Threshold:
A threshold value determines whether a neuron should be activated or not
activated in a binary step activation function. The activation function
compares the input value to a threshold value. If the input value is greater
than the threshold value, the neuron is activated.

Relu function:
Return Zero when the input value is less then zero and otherwise it returns
the same value that was passed into it that means X>0 they give the output
is x value X<0 they give the output is 0value .

sigmoid function:
return the out in binay value

Feedforward Neural Network


It is a one direction process data network for connect to the inpu from
output.

Convolution Neual Network :


it use in image recognition and object dection it is complex image.

it is detect specific features of input.

6
7

You might also like