From 6c2be2bf65357757e0e50c311be9acfdf7bc1f5d Mon Sep 17 00:00:00 2001
From: Marina von Steinkirch <steinkirch@gmail.com>
Date: Sun, 14 Aug 2016 21:56:44 -0700
Subject: [PATCH] numpy readme

---
 Numpy/README.md  | 60 ++++++++++++++++++++++++++++++++++++++++++++++++
 Numpy/dropout.py | 25 ++++++++++++++++++++
 2 files changed, 85 insertions(+)
 create mode 100644 Numpy/dropout.py

diff --git a/Numpy/README.md b/Numpy/README.md
index e69de29..5a019de 100644
--- a/Numpy/README.md
+++ b/Numpy/README.md
@@ -0,0 +1,60 @@
+## Numpy Resources
+
+### Arrays
+
+* Grid of values, all of the same type.
+* The number of dimensions is the rank of the array.
+* The shape of an array is a tuple of integers giving the size of the array along each dimension.
+
+
+```
+a = np.array([1, 2, 3])  # Create a rank 1 array
+print a.shape            # Prints "(3,)"
+```
+
+```
+numpy.asarray([])
+numpy.asarray([]).shape
+```
+
+
+* Many functions to create arrays:
+
+```
+a = np.zeros((2,2))  # Create an array of all zeros
+b = np.ones((1,2))   # Create an array of all ones
+c = np.full((2,2), 7) # Create a constant array
+d = np.eye(2)        # Create a 2x2 identity matrix
+e = np.random.random((2,2)) # Create an array filled with random values
+```
+
+* Products:
+
+
+```
+x = np.array([[1,2],[3,4]])
+
+v = np.array([9,10])
+w = np.array([11, 12])
+
+# Inner product of vectors
+print v.dot(w)
+print np.dot(v, w)
+
+# Matrix / vector product
+print x.dot(v)
+print np.dot(x, v)
+```
+
+* Sum:
+
+```
+print np.sum(x)  # Compute sum of all elements
+print np.sum(x, axis=0)  # Compute sum of each column
+print np.sum(x, axis=1)  # Compute sum of each row
+```
+
+* Broadcasting is a  mechanism that allows numpy to work with arrays of different shapes when performing arithmetic operations. Frequently we have a smaller array and a larger array, and we want to use the smaller array multiple times to perform some operation on the larger array.
+
+
+
diff --git a/Numpy/dropout.py b/Numpy/dropout.py
new file mode 100644
index 0000000..077a06e
--- /dev/null
+++ b/Numpy/dropout.py
@@ -0,0 +1,25 @@
+""" 
+Inverted Dropout: Recommended implementation example.
+We drop and scale at train time and don't do anything at test time.
+"""
+
+p = 0.5 # probability of keeping a unit active. higher = less dropout
+
+def train_step(X):
+  # forward pass for example 3-layer neural network
+  H1 = np.maximum(0, np.dot(W1, X) + b1)
+  U1 = (np.random.rand(*H1.shape) < p) / p # first dropout mask. Notice /p!
+  H1 *= U1 # drop!
+  H2 = np.maximum(0, np.dot(W2, H1) + b2)
+  U2 = (np.random.rand(*H2.shape) < p) / p # second dropout mask. Notice /p!
+  H2 *= U2 # drop!
+  out = np.dot(W3, H2) + b3
+  
+  # backward pass: compute gradients... (not shown)
+  # perform parameter update... (not shown)
+  
+def predict(X):
+  # ensembled forward pass
+  H1 = np.maximum(0, np.dot(W1, X) + b1) # no scaling necessary
+  H2 = np.maximum(0, np.dot(W2, H1) + b2)
+  out = np.dot(W3, H2) + b3
\ No newline at end of file