PROG5

-

 import numpy as np

x=np.array(([2,4],[5,6],[3,6]),dtype=float)

y=np.array(([92],[83],[89]),dtype=float)

x=x/np.amax(x,axis=0)

y=y/100


def sigmoid(x):

    return 1/(1+np.exp(-x))

def derivatives_sigmoid(x):

    return x*(1-x)


epoch=5000

lr=0.1

inputlayer_neurons=2

hiddenlayer_neurons=3

output_neurons=1


wh=np.random.uniform(size=(inputlayer_neurons,hiddenlayer_neurons))

bh=np.random.uniform(size=(1,hiddenlayer_neurons))

wout=np.random.uniform(size=(hiddenlayer_neurons,output_neurons))

bout=np.random.uniform(size=(1,output_neurons))


for i in range(epoch):

    hinp1=np.dot(x,wh)

    hinp=hinp1+bh

    hlayer_act=sigmoid(hinp)

    outinp1=np.dot(hlayer_act,wout)

    outinp=outinp1+bout

    output=sigmoid(outinp)

    EO=y-output

    outgrad=derivatives_sigmoid(output)

    d_output=EO*outgrad

    EH=d_output.dot(wout.T)


hiddengrad=derivatives_sigmoid(hlayer_act)

d_hiddenlayer =EH*hiddengrad


wout+=hlayer_act.T.dot(d_output)*lr

wh+=x.T.dot(d_hiddenlayer)*lr


print("INPUT:\n"+str(x))

print("ACTUAL OUTPUT:\n"+str(y))

print("PREDICTED OUPUT:\n",output)




    

Comments

Post a Comment

If you have any doubts let me know in comments

Popular posts from this blog

PROG9

-
 import matplotlib.pyplot as plt import pandas as pd import numpy as np def kernel(point, xmat, k):     m, n = np.shape(xmat)     weights = np.mat(np.eye((m)))  # eye - identity matrix     for j in range(m):         diff = point - X[j]         weights[j, j] = np.exp(diff * diff.T / (-2.0 * k**2))     return weights def localWeight(point, xmat, ymat, k):     wei = kernel(point, xmat, k)     W = (X.T * (wei * X)).I * (X.T * (wei * ymat.T))     return W def localWeightRegression(xmat, ymat, k):     m, n = np.shape(xmat)     ypred = np.zeros(m)     for i in range(m):         ypred[i] = xmat[i] * localWeight(xmat[i], xmat, ymat, k)     return ypred def graphPlot(X, ypred):     sortindex = X[:, 1].argsort(0)  # argsort - index of the smallest     xsort = X[sortindex][:, 0]     fig = plt.figure()     ax = fig.add_subplot(1, 1, 1)     ax.scatter(bill, tip, color='green')     ax.plot(xsort[:, 1], ypred[sortindex], color='red', linewidth=5)     plt.xlabel('Total bill')  
Read more

ADDING TABLE IN HTML

-
Image
TABLE IN HTML. We can create a Table in html and can list many items in a systematic way which looks good and neat whenever some one visits your page. there are few important tags in creation of a table. let us analyse them <table border="1"> through this tag we can set the border thickness,style and all... <tr> this specifies table row. </tr> closing table row. <th> table head it specifies the top heading of an item list. </th> closes the table head. lets see an example CODE OUTPUT
Read more

PROG8

-
 from sklearn.model_selection import train_test_split from sklearn.neighbors import KNeighborsClassifier from sklearn import datasets # Load dataset iris = datasets.load_iris() print("Iris Data set loaded...") # Split the data into train and test samples x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.1) print("Dataset is split into training and testing...") print("Size of training data and its label", x_train.shape, y_train.shape) print("Size of testing data and its label", x_test.shape, y_test.shape) # Prints Label no. and their names for i in range(len(iris.target_names)):     print("Label", i, "-", str(iris.target_names[i])) # Create object of KNN classifier classifier = KNeighborsClassifier(n_neighbors=12) # Perform Training classifier.fit(x_train, y_train) # Perform testing y_pred = classifier.predict(x_test) # Display the results print("Results of Classification using K-nn wi
Read more