Why neural networks struggle with the Game of Life
Report a link problem
Submission timeline
2007–2026One slot for every year since HN launched. Height is that year's peak points; orange marks a 100+ point or 50+ comment breakout. Select a bar to open its strongest thread.
First comments on top threads
HN comment orderAs someone who knows quite something on this topic, I do not really see what is the surprise here. Let's ignore the title (neural networks don't struggle, they just require a sufficiently large network) and go to the heart of the article, which is that neural networks need to be a lot larger than the most efficient solution to work. What did people expect? That you could use gradient descent to find the optimal solution from a random solution? It…
For everyone reading neither the article nor the paper: - both show neural networks can learn the game of life just fine - the finding is that to learn the rules reliably the networks need to be very over-parameterised (e.g. many times larger than the minimal size needed for hand-crafted weights to perfectly solve the problem) This is not really a new result nor a surprising one, nor does it say anything about the kinds of functions a neural network…
The first top-level comment from each of the four biggest threads, in HN’s own order. Excerpts are shortened; open a comment for full context.
- Breakout years
- 2
- Total points
- 272
- Total comments
- 151
100+ points or 50+ comments
reference only — not used in Hall rules or ranking
reference only — not used in Hall rules or ranking
Every submission
| Date | Title as submitted | By | Points | Comments |
|---|---|---|---|---|
| 2020-09-16 | Why neural networks struggle with the Game of Life | bendee983 | 1 | 0 |
| 2020-09-23 | Why neural networks struggle with the Game of LifeFirst breakout · Best thread | tosh | 141 | 68 |
| 2024-05-17 | Why neural networks struggle with the Game of Life (2020)Latest 20+ point return | DeathArrow | 130 | 83 |