To develop a neural network regression model for the given dataset.

The Neural network model contains input layer,two hidden layers and output layer.Input layer contains a single neuron.Output layer also contains single neuron.First hidden layer contains six neurons and second hidden layer contains seven neurons.A neuron in input layer is connected with every neurons in a first hidden layer.Similarly,each neurons in first hidden layer is connected with all neurons in second hidden layer.All neurons in second hidden layer is connected with output layered neuron.Relu activation function is used here .It is linear neural network model(single input neuron forms single output neuron).

Loading the dataset

Split the dataset into training and testing

Create MinMaxScalar objects ,fit the model and transform the data.

Build the Neural Network Model and compile the model.

Train the model with the training data.

Plot the performance plot

Evaluate the model with the testing data.

# Developed By:harish.g
# Register Number:212220230021

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

df=pd.read_csv("dl2.csv")
df.head()
x=df[['input']].values
x
y=df[['output']].values
y
xtrain,xtest,ytrain,ytest=train_test_split(x,y,test_size=0.3,random_state=40)

scaler=MinMaxScaler()
scaler.fit(xtrain)
scaler.fit(xtest)
xtrain1=scaler.transform(xtrain)
xtest1=scaler.transform(xtest)

model=Sequential([
    Dense(6,activation='relu'),
    Dense(7,activation='relu'),
    Dense(1)
])
model.compile(optimizer='rmsprop',loss='mse')
model.fit(xtrain1,ytrain,epochs=4000)
lossmodel=pd.DataFrame(model.history.history)
lossmodel.plot()
model.evaluate(xtest1,ytest)

xn1=[[77]]
xn11=scaler.transform(xn1)
model.predict(xn11)

Thus,the neural network regression model for the given dataset is developed.