Self-supervised learning is the learning method for Deep Learning models that tries to capture meaningful features without the supervision of humans that force the model to map input data to specific labels. There are several self-supervised learning methods that are mentioned in 10L -- Self-supervised learning in computer vision. In this article, I share one method that I made (as far as I know). The proposed method uses the vector sum logic that is told in the Future Research Section of VeriMedi: Pill Identification using Proxybased Deep Metric Learning and Exact Solution. For calculating the loss, I used Euler's number because of its graph.