✳flâneur — a map of the web's best reading

Ten Patterns and Antipatterns of Deep Learning Experimentation | by Dmitrii Khizbullin | Towards AI

pub.towardsai.net · 1,594 words · saved by 1 readers

In this article, I present a list of patterns and antipatterns I have collected from 10 years of experience as a deep learning engineer. Deep learning engineering is all about experimentation. Coming up with the initial minimal viable product is frequently very fast. In contrast, most of a deep learning project life cycle is taken by iterative improvement of the code and metrics/score. More often than not, the road to the high score compounds from the multitude of marginal improvements discovered in extensive experimentation. In my practice, only one of 5 or even one of 10 experiments improves the score. It is essential to streamline the process of experimentation, especially when working in a team. First of all, let’s clarify the used terms. In the following material, I consider maximizing a single metric, further called “the metric”. By the baseline, I mean the state of the code and the value of the metric that contains no change under consideration. By regression, I imply a decrease

Deep Learning Experimentation Antipattern Patterns Science Ten Patterns and Antipatterns of Deep Learning Experimentation Dmitrii Khizbullin 7 min read · Nov 8, 2023 -- 2 Listen Share Press enter or click to view image in full size The image is generated by DALL-E 3 from the author’s prompt. Introduction In this article, I present a list of patterns and antipatterns I have collected from 10 years of experience as a deep learning engineer. Deep learning engineering is all about experimentation. Coming up with the initial minimal viable product is frequently very fast. In contrast, most of a dee

Explore this link on the map →

related reading