Lab Assessment A simple Artificial Neuron has a summer and an activation (transfer) function connected in series as shown in the figure below. For a single input neuron, shown in the figure, there is a single input ' p ' weighted by a weight ' w ' added to a bias value ' b '. The result of summing these quantities is given as ' n=wp+b '. This value is passed to a transfer function ' f ' to obtain a put ' a ' of the neuron in a predefined desired range. Transfer functions may be linear or non-linear, clipged or unclipped, continuous or not. Thus, different transfer functions have been proposed over the years to obtain desired benefits from them. A few transfer functions are presented below for reference. These transfer functions were discussed in class. You are required to implement the functionality of each of these transfer functions and draw the output of the transfer function. Q1. Plot the output of the Jogsiggoid function for n=5 to 5 [2 marks] Answer: The first one has been done as an example. import numel as np import mateletlib.puplet as plt \#Define the transfer function def logsieggid (z) : return 1.0 [(1+pexp/z]} \#Define two arrays for storing x and y axis values y=[] x[] \#for the range 5 to 5 calculate the output of transfer function for p in range (5,6) : c.apperd(p) z= Jogsigmgid (p) hepRegd[z] \#Print the x and y axis values for confidence building print x ) print /y) \# plotting the points plt.plot (x,y) Q2. Plot the output of the hardlip transfer function for n=5 to 5 [2 marks] Q3. Plot the output of the linear transfer function for n=5 to 5 [2 marks] Q4. Plot the output of the than transfer function for n=5 to 5 [2 marks] Q5. Plot the output of the positive linear transfer function for n=5 to 5 [2 marks] References: Top 5 programming languages for Al, Pvthon for Al and machine learning