You always have to tradeoff something

↑

⇐ ПредыдущаяСтр 13 из 13

Speed vs. memory, battery life vs. accuracy, fairness vs. accuracy, precision vs. recall, ease of implementation vs. maintainability, …

8. Everything is more complicated than you think
Analogous to sticker shock in shopping, there is “effort shock” in working. Even most seasoned researchers engineers experience effort shock, either because they underestimate 1) the engineering issues dealing with large datasets, 2) the complexity of the domain they are wrestling with, and 3) adversaries. There is also a 4th reason for effort shock I call the Karate Kid effect — most papers we read make things appear simpler than they are by not noting the million failures that came before the linear success narrative that gets documented. As a result, papers are not research but a result of doing research. You will never experience doing research by reading papers for that reason, and you will develop a skewed sense of effort.

9. You will always under-provision resources
This is a combination of #8 and the fact that any model remotely successful can collapse due to its own success if not planned properly.

10. One size never fits all. Your model will make embarrassing errors all the time despite your best intentions
Corner cases and long fat tail of failure modes will haunt you. For many, thankfully, non-critical ML deployments this is no big deal. At the worst, it will make a funny tweet. But if you work in healthcare or some other high-risk situation ML deployments will be a nightmare because of these.

11. Every old idea will be proposed again with a different name and a different presentation, regardless of whether it works
Schimdhuber may be making a larger point. Nobody listens to the man, and like him, we rehash old wines in new bottles, and are forced repeat historical mistakes.

12. Perfection has been reached not when there is nothing left to add, but when there is nothing left to take away
True with everything in life and also in machine learning for the Real World. Alas, our conference reviewing process with its penchant for “novelty” creates unwanted arXiv-spam with a lot of garbage that doesn’t need to exist in the first place. Unless doing “science” incentivizes publicizing what works as opposed to what’s new, I don’t see this changing.

P.S. I am intentionally using Machine Learning, instead of AI or Deep Learning everywhere here. The former is pretentious, and the latter is a branding exercise, fighting which is a lost cause. But you could substitute either terminology for your taste.

Questions:

1. Why the dataset defines the problem?

2. What difference between science research and engineering research?

3. Why the Real World will reject your model?

4. Why some things in life can never be fully appreciated or understood?

5. What we need to do if we cant solve the problem?

Dictionary:

1. Science research - научное исследование

2. Engineering research - нженерное исследование

3. The goal - цель

4. ML (Machine learning) - машинное обучение

5. Dataset - набор данных

6. No-brainer - легкая задача

7. Fancy model - модная модель

8. To reject - отвергать

9. Conjecture - следствие

10. Mercilessly - нещадно

11. To parse - разбирать

12. Trade-off - компромисс

13. Under-provision - под представлением

14. Corner cases - угловые(крайние) случаи

15. Rehash - перевариваем, переделываем

16. Penchant - склонность

17. Mistakes - ошибки

18. Effort - усилия

19. Narrative - описание

20. Implementation - реализация

Познавательные статьи:



Как правильно слушать собеседника

Типичные ошибки при выполнении бросков в баскетболе

Принятие христианства на Руси и его значение

Средства массовой информации США