Bug fix: cannot train with RMSprop (#19)

Issue
---
When trying to train with RMSprop learning method, Theano raised a TypeError.

Fix
---
Changed optimization.py line 157 :
```
accumulators = [theano.shared(np.zeros_like(p.get_value()).astype(np.float32)) for p in params]
```

To:
```
accumulators = [theano.shared(np.zeros_like(p.get_value()).astype(floatX)) for p in params]
```

Author: YoannDupont

optimization.py

@@ -154,7 +154,7 @@ def rmsprop(self, cost, params, lr=0.001, rho=0.9, eps=1e-6):
         lr = theano.shared(np.float32(lr).astype(floatX))
 
         gradients = self.get_gradients(cost, params)
-        accumulators = [theano.shared(np.zeros_like(p.get_value()).astype(np.float32)) for p in params]
+        accumulators = [theano.shared(np.zeros_like(p.get_value()).astype(floatX)) for p in params]
 
         updates = []