diff --git a/.idea/encodings.xml b/.idea/encodings.xml
new file mode 100644
index 0000000..97626ba
--- /dev/null
+++ b/.idea/encodings.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/keras-contrib.iml b/.idea/keras-contrib.iml
new file mode 100644
index 0000000..e98082a
--- /dev/null
+++ b/.idea/keras-contrib.iml
@@ -0,0 +1,12 @@
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100644
index 0000000..bc2d718
--- /dev/null
+++ b/.idea/misc.xml
@@ -0,0 +1,29 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000..d4181d1
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..94a25f7
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
new file mode 100644
index 0000000..63feacb
--- /dev/null
+++ b/.idea/workspace.xml
@@ -0,0 +1,209 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ true
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 1485340173501
+
+
+ 1485340173501
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/keras_contrib/layers/advanced_activations.py b/keras_contrib/layers/advanced_activations.py
index 6b39244..199600b 100644
--- a/keras_contrib/layers/advanced_activations.py
+++ b/keras_contrib/layers/advanced_activations.py
@@ -2,3 +2,75 @@ from .. import initializations
from keras.engine import Layer
from .. import backend as K
import numpy as np
+
+
+class PELU(Layer):
+ """Parametric Exponential Linear Unit.
+ It follows:
+ `f(x) = alphas * x for x < 0`,
+ `f(x) = x for x >= 0`,
+ where `alphas` is a learned array with the same shape as x.
+ # Input shape
+ Arbitrary. Use the keyword argument `input_shape`
+ (tuple of integers, does not include the samples axis)
+ when using this layer as the first layer in a model.
+ # Output shape
+ Same shape as the input.
+ # Arguments
+ init: initialization function for the weights.
+ weights: initial weights, as a list of a single Numpy array.
+ shared_axes: the axes along which to share learnable
+ parameters for the activation function.
+ For example, if the incoming feature maps
+ are from a 2D convolution
+ with output shape `(batch, height, width, channels)`,
+ and you wish to share parameters across space
+ so that each filter only has one set of parameters,
+ set `shared_axes=[1, 2]`.
+ # References
+ - [PARAMETRIC EXPONENTIAL LINEAR UNIT FOR DEEP CONVOLUTIONAL NEURAL NETWORKS](https://arxiv.org/abs/1605.09332v3)
+ """
+
+ def __init__(self, init='zero', weights=None, shared_axes=None, **kwargs):
+ self.supports_masking = True
+ self.init = initializations.get(init)
+ self.initial_weights = weights
+ if not isinstance(shared_axes, (list, tuple)):
+ self.shared_axes = [shared_axes]
+ else:
+ self.shared_axes = list(shared_axes)
+ super(PELU, self).__init__(**kwargs)
+
+ def build(self, input_shape):
+ param_shape = list(input_shape[1:])
+ self.param_broadcast = [False] * len(param_shape)
+ if self.shared_axes[0] is not None:
+ for i in self.shared_axes:
+ param_shape[i - 1] = 1
+ self.param_broadcast[i - 1] = True
+
+ # Initialised as ones to emulate the default ELU
+ self.alphas = K.ones(param_shape, dtype=K.floatx(),
+ name='{}_alphas'.format(self.name))
+ self.betas = K.ones(param_shape, dtype=K.floatx(),
+ name='{}_betas'.format(self.name))
+
+ self.trainable_weights = [self.alphas, self.betas]
+
+ if self.initial_weights is not None:
+ self.set_weights(self.initial_weights)
+ del self.initial_weights
+
+ def call(self, x, mask=None):
+ pos = K.relu(x) * (self.alphas / self.betas)
+ if K.backend() == 'theano':
+ neg = (K.pattern_broadcast(self.alphas, self.param_broadcast) *
+ (K.exp(x / self.betas) - 1))
+ else:
+ neg = self.alphas * (K.exp(x / self.betas) - 1)
+ return pos + neg
+
+ def get_config(self):
+ config = {'init': self.init.__name__}
+ base_config = super(PELU, self).get_config()
+ return dict(list(base_config.items()) + list(config.items()))