I wrote my first neural network
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
I have been interested in neural nets since the 90's. I've done quite a bit of reading, but never gotten around to writing code. I used Gemini in place of Wikipedia to fill in the gaps of my knowledge. The coolest part of this was learning about dual numbers. You can see in early commits that I did not yet know about auto-diff; I was thinking I'd have to integrate a CAS library or something. Now, I'm off to play with TensorFlow.
HN · launched Mar 14, 2026 · 6 upvotes (top 71%) · 0 views
Niche: deep learning frameworks · 48 launches, 0 in the last 7 days · Explore this niche →
Category and tags
- Horizontal
- Dev tools
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 48 launches in deep learning frameworks →
Could you build this?
Yes Writing a basic neural network from scratch (forward pass, backpropagation, or dual-number automatic differentiation) is a classic educational project well within the capability of an AI coding assistant.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one : 242 launches clear the similarity bar, closest 8 shown.
Attention rank: #184 of 243 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 136 days after the earliest competitor.
- I wrote a technical history book on Lisp · hn · 2026-02-17 · 252 upvotes · similarity 0.51
- I quit coding years ago. AI brought me back · hn · 2026-01-19 · 314 upvotes · similarity 0.49
- Make AI motion videos with text · hn · 2026-02-02 · 6 upvotes · similarity 0.44
- Strange Attractors · hn · 2025-10-31 · 804 upvotes · similarity 0.44
- Maths, CS and AI Compendium · hn · 2026-02-16 · 88 upvotes · similarity 0.44
- A)I updated my vimrc · hn · 2025-10-31 · 5 upvotes · similarity 0.43
- We beat Gemini Embedding 2 by training only 16M params (open weights) · hn · 2026-07-10 · 7 upvotes · similarity 0.43
- MacMind · hn · 2026-04-16 · 159 upvotes · similarity 0.42
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.