diff --git a/maths/inter_quartile_range.py b/maths/inter_quartile_range.py
new file mode 100644
index 000000000..91a5eb330
--- /dev/null
+++ b/maths/inter_quartile_range.py
@@ -0,0 +1,61 @@
+"""
+This is the implementation of inter_quartile range (IQR).
+
+function takes the list of numeric values as input
+and return the IQR as output.
+
+Script inspired from its corresponding Wikipedia article
+https://en.wikipedia.org/wiki/Interquartile_range
+"""
+
+from typing import List
+
+
+def find_median(x: List[float]) -> float:
+    """
+    This is the implementation of median.
+    :param x: The list of numeric values
+    :return: Median of the list
+    >>> find_median([1,2,2,3,4])
+    2
+
+    >>> find_median([1,2,2,3,4,4])
+    2.5
+
+
+    """
+    length = len(x)
+    if length % 2:
+        return x[length // 2]
+    return float((x[length // 2] + x[(length // 2) - 1]) / 2)
+
+
+def inter_quartile_range(x: List[float]) -> float:
+    """
+    This is the implementation of inter_quartile
+    range for a list of numeric.
+    :param x: The list of data point
+    :return: Inter_quartile range
+
+    >>> inter_quartile_range([4,1,2,3,2])
+    2.0
+
+    >>> inter_quartile_range([25,32,49,21,37,43,27,45,31])
+    18.0
+    """
+    length = len(x)
+    if length == 0:
+        raise ValueError
+    x.sort()
+    q1 = find_median(x[0: length // 2])
+    if length % 2:
+        q3 = find_median(x[(length // 2) + 1: length])
+    else:
+        q3 = find_median(x[length // 2: length])
+    return q3 - q1
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod()
diff --git a/neural_network/activation_functions/mish_activation.py b/neural_network/activation_functions/mish_activation.py
deleted file mode 100644
index c292f76f1..000000000
--- a/neural_network/activation_functions/mish_activation.py
+++ /dev/null
@@ -1,40 +0,0 @@
-"""
-Implements the Mish activation functions.
-
-The function takes a vector of K real numbers input and then
-applies the mish function, x*tanh(softplus(x) to each element of the vector.
-
-Script inspired from its corresponding Wikipedia article
-https://en.wikipedia.org/wiki/Rectifier_(neural_networks)
-
-The proposed paper link is provided below.
-https://arxiv.org/abs/1908.08681
-"""
-
-import numpy as np
-from maths.tanh import tangent_hyperbolic as tanh
-
-
-def mish_activation(vector: np.ndarray) -> np.ndarray:
-    """
-    Implements the Mish function
-
-    Parameters:
-        vector: np.array
-
-    Returns:
-        Mish (np.array): The input numpy array after applying tanh.
-
-    mathematically, mish = x * tanh(softplus(x)  where
-    softplus = ln(1+e^(x)) and tanh = (e^x - e^(-x))/(e^x + e^(-x))
-    so, mish can be written as x * (2/(1+e^(-2 * softplus))-1
-
-    """
-    soft_plus = np.log(np.exp(vector) + 1)
-    return vector * tanh(soft_plus)
-
-
-if __name__ == "__main__":
-    import doctest
-
-    doctest.testmod()