diff --git a/Coursera/Lesson1/Week2/broadcasting.py b/Coursera/Lesson1/Week2/broadcasting.py
new file mode 100644
index 0000000..2d4f487
--- /dev/null
+++ b/Coursera/Lesson1/Week2/broadcasting.py
@@ -0,0 +1,14 @@
+import numpy as np
+A = np.array([[56.0, 0.0, 4.4, 68.0],
+	      [1.2, 104.0, 52.0, 8.0],
+	      [1.8, 135.0, 99.0, 0.9]])
+
+print(A)
+
+cal = A.sum(axis=0)
+print(cal.shape)
+
+print(cal.reshape(1,4))
+
+percentage = 100*A/cal.reshape(1,4)
+print(percentage)
diff --git a/Coursera/Lesson1/Week2/test.py b/Coursera/Lesson1/Week2/test.py
new file mode 100644
index 0000000..007868c
--- /dev/null
+++ b/Coursera/Lesson1/Week2/test.py
@@ -0,0 +1,128 @@
+"""
+supervised learning:
+m = number of examples = size of the data
+m_train = number of training examples
+m_test = number of test examples
+
+x = input vector
+y = output vector 
+y_hat = predicted output vector
+
+nx = length of the input vector
+ny = length of the output vector
+
+w = weight(s) vector(s) of the neural network
+b = bias(s) vector(s) of the neural network
+t_w = transpose matrix of w
+z = t_w * x + b
+sigmoid(z) = 1/(1+math.exp(-z))
+y_hat = a = sigmoid(z)
+
+L(y_hat,y) = loss function applied on a single example
+J(w,b) = cost function = average of L given all examples
+
+common loss function:
+L(y_hat,h) = 1/2*(y-y_hat)**2
+on logistic regression problems:
+L(y_hat,y) = - (y*math.log(y_hat) + (1-y)*math.log(1-y_hat))
+L(a,y) = - (y*math.log(a) + (1-y)*math.log(1-a))
+
+learned about computation graph and computing derivatives that comes with it
+
+make use of the chain rule of derivatives :
+dz/dx = dz/dy * dy/dx
+"""
+
+"dvar is the derivate of the final output variable by the input variable"
+
+"""
+"da" = dL(a,y)/da = -y/a + (1-y)/(1-a)
+"dz" = dL(a,y)/dz = dL/da * da/dz
+"dw" = dL/dw
+"db" = dL/db
+
+however we know that:
+dL/da = -y/a + (1-y)/(1-a)
+da/dz = a(1-a)
+
+dz/dw = x
+dz/db = 1
+
+so:
+dL/dz = a - y
+
+
+
+
+"""
+
+import numpy as np
+import math
+
+
+def logistic_regression(x, y, J=0, dw1=0, dw2=0, db=0,l=0.05):
+	m = x.shape[0]
+	z = np.zeros_like(x[0])
+	w1 = random.random()
+	w2 = random.random()
+	b = random.random()
+	for i in range(m):
+		z[i] = np.dot(w, x[i]) + b
+		a_i = sigmoid(z[i])
+		Jt = -(y[i]*math.log(a_i) + \
+			(1-y[i]) * math.log(1-a_i))
+		dz_i = a_i - y[i]
+		dw1 += x1_i * dz_i
+		dw2 += x2_i * dz_i
+		db += dz_i
+	J/=m
+	dw1/=m; dw2/=m; db/=m
+	w1 -= l*dw1
+	w2 -= l*dw2
+	b -= l*db
+	return [w,b]
+	
+
+		
+
+
+"""
+J=0 ; dw1=0; dw2=0; db=0 
+for i=1 to m
+	z[i] = t_w * x[i] + b
+	a[i] = sigmoid(z[i])
+	Jt = -[y[i]*log(a[i]) + (1-y[i])*log(1-a[i])]
+	dz[i] = a[i] - y[i]
+	dw1 += x1[i] * dz[i]
+	dw2 += x2[i] * dz[i]
+	db += dz[i]
+
+J/=m
+dw1/=m; dw2/=m; db/=m
+
+ w1 -= l*dw1
+ w2 -= l*dw2
+ b -= l*db
+"""
+
+
+"""Vectorization:
+Z = t_w * X + B
+
+Z = np.dot(w, X) + b
+A = sigmoid(Z)
+
+
+Implement Logistic Regression
+
+Z = tw*X+b = np.dot(w.T,X) + b
+A = sigmoid(Z)
+dZ = A-Y
+dW = 1/m * X*dZ.T
+dB = 1/m* np.sum(dZ)
+
+w -= alpha * dW
+b -= alpha * dB
+
+
+"""
diff --git a/Coursera/Lesson1/Week2/vectorization.py b/Coursera/Lesson1/Week2/vectorization.py
new file mode 100644
index 0000000..c9b03ff
--- /dev/null
+++ b/Coursera/Lesson1/Week2/vectorization.py
@@ -0,0 +1,29 @@
+import numpy as np
+
+a = np.array([1,2,3,4])
+print(a)
+
+
+import time 
+
+a = np.random.rand(1000000)
+b = np.random.rand(1000000)
+
+tic = time.time()
+c = np.dot(a,b)
+
+toc = time.time()
+
+print("Vectorized version:" + str(1000*(toc-tic)) + "ms")
+
+c = 0
+tic = time.time()
+for i in range(1000000):
+	c += a[i] * b[i]
+
+toc = time.time()
+
+print(c)
+print("For loop:" + str(1000*(toc-tic)) + "ms")
+
+
diff --git a/Coursera/Lesson1/Week2/vectorization2.py b/Coursera/Lesson1/Week2/vectorization2.py
new file mode 100644
index 0000000..adab6ba
--- /dev/null
+++ b/Coursera/Lesson1/Week2/vectorization2.py
@@ -0,0 +1,25 @@
+import numpy as np
+
+a = np.array([1,2,3,4])
+
+print(a)
+
+import time
+a = np.random.rand(1000000)
+b = np.random.rand(1000000)
+
+tic = time.time()
+c = np.dot(a,b)
+toc = time.time()
+
+print("Vectorized version:" + str(1000*(toc-tic)) + "ms")
+
+c = 0
+tic = time.time()
+for i in range(1000000):
+	c += a[i]*b[i]
+toc = time.time()
+
+print("For loop:" + str(1000*(toc-tic)) + "ms")
+
+
diff --git a/Coursera/Lesson1/Week2/vectors.py b/Coursera/Lesson1/Week2/vectors.py
new file mode 100644
index 0000000..b1d6710
--- /dev/null
+++ b/Coursera/Lesson1/Week2/vectors.py
@@ -0,0 +1,11 @@
+import numpy as np
+
+a = np.random.randn(5)
+
+print(a) 
+print(a.shape)
+
+print(a.T)
+
+
+print(np.dot(a, a.T))
diff --git a/gensim/.DS_Store b/gensim/.DS_Store
new file mode 100644
index 0000000..5008ddf
Binary files /dev/null and b/gensim/.DS_Store differ