WEEK 7

In this workshop, I aimed to train a model to differentiate between Chinese actress and me. The goal was for the model to classify these items based on images captured via webcam. Actrually, the model performed reasonably well, because I was satisfied with the result.(No matter the outcome, I’ll accept it because they are all beautiful.)

If the dataset lacked diversity in terms of gender, race, or age, the model might fail to generalize effectively, perpetuating stereotypes or excluding certain groups. This reinforces the importance of ensuring inclusive and representative data when training models involving human subjects.I only had women take the test because all the model inputs used as references were female.

If I have enough time, I will expanded the dataset: Collected more varied samples under different conditions (e.g., different lighting, backgrounds, and angles) to improve the model's accuracy.The performance of machine learning models heavily relies on the quantity, quality, and diversity of the training data.Overall, this workshop illustrated both the potential and the pitfalls of machine learning. It serves as a reminder that while the technology is powerful, its effectiveness and fairness are only as good as the care and thoughtfulness invested in its development.