Skip to content

Simplify learning rate decay #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
marjinal1st wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Simplify learning rate decay #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions BackPropagationNN.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,10 +14,10 @@ def sigmoid(x):
def dsigmoid(y):
return y * (1.0 - y)

# using tanh over logistic sigmoid is recommended
# using tanh over logistic sigmoid is recommended
def tanh(x):
return math.tanh(x)

# derivative for tanh sigmoid
def dtanh(y):
return 1 - y*y
Expand Down Expand Up @@ -46,7 +46,7 @@ def __init__(self, input, hidden, output, iterations, learning_rate, momentum, r
self.learning_rate = learning_rate
self.momentum = momentum
self.rate_decay = rate_decay

# initialize arrays
self.input = input + 1 # add 1 for bias node
self.hidden = hidden
Expand All @@ -63,7 +63,7 @@ def __init__(self, input, hidden, output, iterations, learning_rate, momentum, r
output_range = 1.0 / self.hidden ** (1/2)
self.wi = np.random.normal(loc = 0, scale = input_range, size = (self.input, self.hidden))
self.wo = np.random.normal(loc = 0, scale = output_range, size = (self.hidden, self.output))

# create arrays of 0 for changes
# this is essentially an array of temporary values that gets updated at each iteration
# based on how much the weights need to change in the following iteration
Expand Down Expand Up @@ -180,8 +180,8 @@ def train(self, patterns):
if i % 10 == 0:
print('error %-.5f' % error)
# learning rate decay
self.learning_rate = self.learning_rate * (self.learning_rate / (self.learning_rate + (self.learning_rate * self.rate_decay)))
self.learning_rate /= (1.0 + self.rate_decay)

def predict(self, X):
"""
return list of predictions after training algorithm
Expand All @@ -202,12 +202,12 @@ def load_data():
y = data[:,0:10]
#y[y == 0] = -1 # if you are using a tanh transfer function make the 0 into -1
#y[y == 1] = .90 # try values that won't saturate tanh

data = data[:,10:] # x data
#data = data - data.mean(axis = 1)
data -= data.min() # scale the data so values are between 0 and 1
data /= data.max() # scale

out = []
print data.shape

Expand Down