![\"\"](\"https:\/\/cde.nus.edu.sg\/isem\/wp-content\/uploads\/sites\/12\/2024\/02\/machine-learning.jpg\")
<\/p>\n<\/p>\n
Machine learning enables businesses to speed up the pace of work, reduce errors and improve accuracy. One example of this is image classification where a machine processes images along a production line to identify defective products.<\/p>\n
The ability to train machines to recognize images presents a huge opportunity for many organizations. In particular, visual tasks that are currently performed by humans can potentially be automated, resulting in significant cost savings.<\/p>\n
Recently, I conducted a short image classification workshop. In that workshop, we explain the basics behind how a machine can be trained to recognize different images. In addition, we had a step-by-step guided segment where participants built their own image classifier in MS Excel.<\/p>\n
![\"\"](\"https:\/\/cde.nus.edu.sg\/isem\/wp-content\/uploads\/sites\/12\/2024\/02\/ML-images-300x238.jpg\")
<\/p>\n
The images were made up of 28 by 28 pixels (i.e., 784 input values). Conditional formatting was used to help viewers visualize the images (see image below).<\/p>\n
To keep things simple, we used a small neural network to implement this. In particular, we only had 16 nodes in our input layer, 12 nodes in a single hidden layer and 10 output nodes. We reduced the 784 input values into just 16 values where each value is obtained by taking the average of 7 X 7 pixels. You can think of this as a very simple image compression (although I will have problems restoring back the original image, but I don’t have to worry about that here).<\/p>\n
The node values were computed using Rectified Linear Unit (ReLU) activation functions which are very simple functions that can easily be executed in MS Excel.<\/p>\n
You can view the video below for full details: Download template<\/a><\/span> | |\u00a0Download solution<\/a><\/span><\/p>\n Dr TAN Chin Hon 5 Jan 2022<\/p>\n