diff --git a/onn/layer.py b/onn/layer.py
index ce91094..f8987f0 100644
--- a/onn/layer.py
+++ b/onn/layer.py
@@ -1,7 +1,6 @@
 from .layer_base import *
 from .initialization import *
 from .float import *
-from .regularizer import Regularizer
 
 
 # Nonparametric Layers {{{1
@@ -77,21 +76,6 @@ class Sum(Layer):
         return edges[0]  # TODO: does this always work?
 
 
-class ActivityRegularizer(Layer):
-    def __init__(self, reg):
-        super().__init__()
-        assert isinstance(reg, Regularizer), reg
-        self.reg = reg
-
-    def forward(self, X):
-        self.X = X
-        self.loss = np.sum(self.reg.forward(X))
-        return X
-
-    def backward(self, dY):
-        return dY + self.reg.backward(self.X)
-
-
 class Dropout(Layer):
     def __init__(self, dropout=0.0):
         super().__init__()
diff --git a/onn/regularizer.py b/onn/regularizer.py
index 37887c3..eec9888 100644
--- a/onn/regularizer.py
+++ b/onn/regularizer.py
@@ -1,5 +1,6 @@
 import numpy as np
 
+from .layer import Layer
 from .float import *
 
 
@@ -7,6 +8,21 @@ class Regularizer:
     pass
 
 
+class ActivityRegularizer(Layer):
+    def __init__(self, reg):
+        super().__init__()
+        assert isinstance(reg, Regularizer), reg
+        self.reg = reg
+
+    def forward(self, X):
+        self.X = X
+        self.loss = np.sum(self.reg.forward(X))
+        return X
+
+    def backward(self, dY):
+        return dY + self.reg.backward(self.X)
+
+
 class L1L2(Regularizer):
     def __init__(self, l1=0.0, l2=0.0):
         self.l1 = _f(l1)