shashwatwork

iter = 0
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        # Load images as Variable
        images = Variable(images.view(-1, 28*28))
        labels = Variable(labels)
        
        # Clear gradients w.r.t. parameters
        optimizer.zero_grad()
        

shashwatwork

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

def sigmoid(x, derivative=False):
    if (derivative == True):
        return x * (1 - x)
    return 1 / (1 + np.exp(-x))
    
x = sigmoid(x)

shashwatwork

import numpy as np

def tanh(x, derivative=False):
    if (derivative == True):
        return (1 - (x ** 2))
    return np.tanh(x)
  
  x = tanh(x)
  print(x)

shashwatwork

import numpy as np

def relu(x, derivative=False):
    if (derivative == True):
        for i in range(0, len(x)):
            for k in range(len(x[i])):
                if x[i][k] > 0:
                    x[i][k] = 1
                else:
                    x[i][k] = 0

shashwatwork

import numpy as np

def arctan(x, derivative=False):
    if (derivative == True):
        return (np.cos(x) ** 2)
    return np.arctan(x)


x = arctan(x)
print(x)

shashwatwork

import numpy as np

def step(x, derivative=False):
    if (derivative == True):
        for i in range(0, len(x)):
            for k in range(len(x[i])):
                if x[i][k] > 0:
                    x[i][k] = 0
        return x
    for i in range(0, len(x)):

shashwatwork

import numpy as np


def squash(x, derivative=False):
    if (derivative == True):
        for i in range(0, len(x)):
            for k in range(0, len(x[i])):
                if x[i][k] > 0:
                    x[i][k] = (x[i][k]) / (1 + x[i][k])
                else:

shashwatwork

import numpy as np

def gaussian(x, derivative=False):
    if (derivative == True):
        for i in range(0, len(x)):
            for k in range(0, len(x[i])):
                x[i][k] = -2* x[i][k] * np.exp(-x[i][k] ** 2)
    for i in range(0, len(x)):
        for k in range(0, len(x[i])):
            x[i][k] = np.exp(-x[i][k] ** 2)

shashwatwork

import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets,linear_model
from sklearn.metrics import mean_squared_error,r2_score
diabetes=datasets.load_diabetes()
diabetes_X=diabetes.data[:,np.newaxis,2]
diabetes_X_train=diabetes_X[:-30] #splitting data into training and test sets
diabetes_X_test=diabetes_X[-30:]
diabetes_y_train=diabetes.target[:-30] #splitting targets into training and test sets
diabetes_y_test=diabetes.target[-30:]

shashwatwork

import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model
xmin,xmax=-7,7 #Test set; straight line with Gaussian noise
n_samples=77
np.random.seed(0)
x=np.random.normal(size=n_samples)
y=(x>0).astype(np.float)
#Import Library
from sklearn.linear_model import LogisticRegression