added to glossary and fixed syntax issues with activation_functions.py (

#69)

code/activation_functions.py

@@ -8,10 +8,10 @@
 
 ### Functions ###
 
-def linear(z,m)
+def linear(z,m):
 	return m*z
 
-def elu(z,alpha)
+def elu(z,alpha):
 	return z if z >= 0 else alpha*(e^z -1)
 
 def leakyrelu(z, alpha):
@@ -24,19 +24,18 @@ def sigmoid(z):
   return 1.0 / (1 + np.exp(-z))
 
 def tanh(z):
-	return (np.exp(z) - np.exp(-z)) 
-	/ (np.exp(z) + np.exp(-z))
+	return (np.exp(z) - np.exp(-z)) / (np.exp(z) + np.exp(-z))
 
 
 
 
 ### Derivatives ###
 
-def linear_prime(z,m)
+def linear_prime(z,m):
 	return m
 
-def elu_prime(z,alpha)
-	return 1 if z > 0 else alpha*e^z
+def elu_prime(z,alpha):
+	return 1 if z > 0 else alpha*np.exp(z)
 
 def leakyrelu_prime(z, alpha):
 	return 1 if z > 0 else alpha

docs/glossary.rst

@@ -154,8 +154,7 @@ Model
 .. _glossary_neural_networks:
 
 Neural Networks
-  A model that, taking inspiration from the brain, is composed of layers (at least one of which is hidden) consisting of simple connected units or neurons followed by nonlinearities.
-  It can be trained to recognize patterns. Neurons in each layer learn increasingly abstract representations of the data.
+  Neural Networks are mathematical algorithms modeled after the brain's architecture, designed to recognize patterns and relationships in data. 
 
 .. _glossary_normalization:
 
@@ -179,7 +178,14 @@ Overfitting
 .. _glossary_parameters:
 
 Parameters
-  Be the first to `contribute! <https://github.com/bfortuner/ml-cheatsheet>`__
+  Parameters are properties of training data learned by training a machine learning model or classifier. They are adjusted using optimization algorithms and unique to each experiment. 
+
+  Examples of parameters include:
+
+  - weights in an artificial neural network
+  - support vectors in a support vector machine
+  - coefficients in a linear or logistic regression
+
 
 .. _glossary_precision:
 
@@ -216,7 +222,7 @@ Regression
 .. _glossary_regularization:
 
 Regularization
-  Contribute a definition!
+  Regularization is a technique utilized to combat the overfitting problem. This is achieved by adding a complexity term to the loss function that gives a bigger loss for more complex models 
 
 .. _glossary_reinforcement_learning: