|Written by Nikos Vaggalis|
|Friday, 11 January 2019|
|A fun and practical introduction to the underpinnings of AI.
Working with AI is increasingly easier thanks to new and versatile libraries which encapsulate all the logic so you don’t have to, to the extent that your AI skills are worth less than you think:
As exciting as the progress is, it’s bad news for both companies and individuals who have invested heavily in AI skills. Today, they give you a solid competitive advantage, as training a competent ML engineer requires plenty of time spent reading papers, and a solid math background to start with. However, as the tools get better, this won’t be the case anymore. It’ll become more about reading tutorials than scientific papers. If you don’t realize your advantage soon, a band of interns with a library may eat your lunch.
Here’s an overview of its contents:
2. Our first neural net!
3. How do they learn? Propagation
4. How do they learn? Part 2 — Structure
5. How do they learn? Part 3 — Layers
6. Working with objects & 7. Learning more than numbers
8. Counting with neural nets
9. Stock market prediction – Normalization & 10. Stock market prediction — Predict next & 11. Stock market prediction — Predict next 3 steps
12. Recurrent neural networks learn math
13. Lo-fi number detection
14. Writing a children’s book with a recurrent net
15. Sentiment detection
16. Recurrent neural networks with … inputs? outputs? How?
17. Simple reinforcement learning
18. Building a recommendation engine
19. Closing thoughts
The closing thoughts are that Brain.js is a great library and this is a great tutorial. Even if you don’t want to code, you ought to watch it if you are interested in gaining a good encyclopedic overview of how neural networks function in a way that is practical and very easy to understand.