talk · HACKER NEWS RECOMMENDATION
Connections between physics and deep learning
MITCBMM · 3 HN recommenders · 3 recommendation months
Recommended by 3 Hacker News commenters across 3 months (2016–2026).
SignalTube analysis
Among 37 other talk videos tagged Machine learning & deep learning, the mean is 2.7 distinct HN recommenders. This video has 3 distinct HN recommenders, close to that mean. Recommendations span 3 distinct months; the peer average is 2.5 months. This is a data-derived comparison, not a human review or quality rating.
50% of its 6 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2016–2026; those years describe discussion history, not upload date. Its verified runtime is 51 minutes 46 seconds. YouTube lists its publication date as 2016-08-30.
- Channel / speaker
- MITCBMM
- Verified runtime
- 51m 46s
- YouTube upload date
- 2016-08-30
- Hacker News mention years
- 2016–2026
SAME TOPIC AND FORMAT
Compare with related videos
The comparison cohort uses other talk videos in Machine learning & deep learning. “Shared recommenders” counts HN users who recommended both videos in the source graph.
| Video | HN recommenders | Recommendation months | Positive label share | Shared recommenders | Runtime | Upload date |
|---|---|---|---|---|---|---|
| Connections between physics and deep learningCurrent video | 3 | 3 | 50% | — | 51m 46s | 2016-08-30 |
| USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?talk · USENIX | 10 | 10 | 50% | No recorded overlap | 51m 22s | 2018-08-16 |
| Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learningtalk · Google TechTalks | 9 | 7 | 82% | No recorded overlap | 48m 10s | 2011-04-11 |
| [1hr Talk] Intro to Large Language Modelstalk · Andrej Karpathy | 9 | 6 | 45% | No recorded overlap | 59m 48s | 2023-11-23 |
THREE SOURCE-BASED CONTEXT POINTS
Why Hacker News recommends it
Each note combines the dataset’s stance label and short rationale; comment bodies are not reproduced. Open the HN source for the original discussion.
The archive classifies this as a contextual reference in “How LLMs Work”. Its short rationale: Tegmark on why deep cheap learning works so well.
The archive classifies this as a strong recommendation in “Why does deep and cheap learning work so well?”. Its short rationale: Physical data has symmetries, making it compressible into small neural circuits.
The archive classifies this as a contextual reference in “Deep Learning and Quantum Entanglement [pdf]”. Its short rationale: Cited among references on how deep learning maps onto physics.