I have attached the requirements which is actually the assignment. kindly find the attachment. As I am trying to make a model between multiple input and multiple output considering uncertainty, I...

I have attached the requirements which is actually the assignment. kindly find the attachment.
As I am trying to make a model between multiple input and multiple output considering uncertainty, I tried it initial stages. Here I attached the codes based on two input and one output (the input and output generated randomly). And it's running well. I have attached the file name "Regression.ipynb"
As I am focusing multiple input and multiple output model using my data, I tried to use my data directly instead of the random data. and then I faced some problem to run the codes. Find the attachment named "Regression_data"
You can either update these codes or make your own codes. But need to remember that you should use Bayes backpropagation method. Because I am focusing on this method which can able to prepare a model considering uncertainty.
Thanks


Uncertainty distribution using bayesian backpropagation in python I need to use my data to the existing codes and prepare a model between input and output using my data. The codes data is in vector form. But my data is in matrix form. So, need to change the codes in matrix form. You can use your codes as well. But It needs to be based on bayes backpropagation. Which actually provides output probability. Because the net structure of this is different than standard neural network. In standard neural network, the weight value is fixed but here the weights are following normal distribution. As a result, the output can be showed as a distribution. For better understanding, check the link that I shared. Here is my data. You should use this data as the input (X) and output (Y) Input Output Laser power Scan speed Overlap rate Hatch distance Relative density Hardness Tensile strength Porosity 320 600 0.25 102.4 0.9739 119 455 2.61 320 600 0.35 88.7 0.9802 130.8 443.33 1.98 320 750 0.25 93.1 0.9774 124.4 448.33 2.26 360 600 0.25 111 0.9688 127.2 431.67 3.12 360 600 0.3 103.6 0.979 135.2 436.67 2.1 360 600 0.35 96.2 0.9725 116.4 441.67 2.75 360 750 0.25 98 0.9732 129.8 430 2.68 360 750 0.3 91.4 0.9817 123.2 441.67 1.83 360 900 0.25 88.9 0.9736 119 420 2.64 360 900 0.3 83 0.9799 127.2 431.67 2.01 400 600 0.25 116.4 0.9559 118.6 420 4.41 400 600 0.35 100.9 0.9812 139.2 438.33 1.88 400 750 0.25 104.7 0.9722 124.8 430 2.78 400 750 0.3 97.7 0.9763 127.4 431.67 2.37 400 900 0.25 94.1 0.9795 125.4 352.2 2.05 400 900 0.3 87.8 0.9651 113.2 383.11 3.49 400 900 0.35 81.5 0.9758 118.4 408.18 2.42 320 750 0.35 80.7 0.9777 127.8 445 2.23 320 900 0.25 81.8 0.9817 127.6 443.33 1.83 320 900 0.3 76.3 0.9784 127.8 446.67 2.16 360 750 0.35 84.9 0.9734 128.8 445 2.66 400 600 0.3 108.6 0.9791 131 445 2.09 320 600 0.3 95.5 0.9801 123.2 450 1.99 320 750 0.3 86.9 0.9737 123.2 443.33 2.63 320 900 0.35 70.9 0.9813 122.6 450 1.87 360 900 0.35 77.1 0.9795 122 446.67 2.05 400 750 0.35 90.7 0.9694 120.8 443.03 3.06 here is the code link you should follow and check the results folder to get the idea about the plot. https://github.com/saxena-mayur/Weight-Uncertainty-in-Neural-Networks/tree/master/Regression You can read this pdf to know about this coding. Specially 5.2 Regression curve (figure 5) https://arxiv.org/pdf/1505.05424 If you need any information, feel free to contact me here: [email protected]