ML 28: Augmentation Adds an Assumption, Not Data
Disclosure: this post was written with the assistance of an AI system (Claude), which wrote the analysis code, ran the experiments and drafted the text. The topic, the constraints, the data choices and the final review are the author’s. Trained on 150 digits, a network scored 0.917. Four times as many real digits raised that by 0.041; four shifted copies of each image changed it by -0.027, pixel noise by +0....