))
Zoom In: An Introduction to Circuits
Manage episode 424744797 series 3498845
Contenu fourni par BlueDot Impact. Tout le contenu du podcast, y compris les épisodes, les graphiques et les descriptions de podcast, est téléchargé et fourni directement par BlueDot Impact ou son partenaire de plateforme de podcast. Si vous pensez que quelqu'un utilise votre œuvre protégée sans votre autorisation, vous pouvez suivre le processus décrit ici https://fr.player.fm/legal.
By studying the connections between neurons, we can find meaningful algorithms in the weights of neural networks.
Many important transition points in the history of science have been moments when science “zoomed in.” At these points, we develop a visualization or tool that allows us to see the world in a new level of detail, and a new field of science develops to study the world through this lens.
For example, microscopes let us see cells, leading to cellular biology. Science zoomed in. Several techniques including x-ray crystallography let us see DNA, leading to the molecular revolution. Science zoomed in. Atomic theory. Subatomic particles. Neuroscience. Science zoomed in.
These transitions weren’t just a change in precision: they were qualitative changes in what the objects of scientific inquiry are. For example, cellular biology isn’t just more careful zoology. It’s a new kind of inquiry that dramatically shifts what we can understand.
The famous examples of this phenomenon happened at a very large scale, but it can also be the more modest shift of a small research community realizing they can now study their topic in a finer grained level of detail.
Source:
https://distill.pub/2020/circuits/zoom-in/
Narrated for AI Safety Fundamentals by Perrin Walker
A podcast by BlueDot Impact.
Learn more on the AI Safety Fundamentals website.
Chapitres
1. Zoom In: An Introduction to Circuits (00:00:00)
2. Three Speculative Claims (00:04:52)
3. Claim 1: Features (00:07:58)
4. Example 1: Curve Detectors (00:11:22)
5. Example 2: High-Low Frequency Detectors (00:16:50)
6. Example 3: Pose-Invariant Dog Head Detector (00:18:43)
7. Polysemantic Neurons (00:20:39)
8. Claim 2: Circuits (00:23:02)
9. Circuit 1: Curve Detectors (00:24:01)
10. Circuit 2: Oriented Dog Head Detection (00:27:48)
11. Circuit 3: Cars in Superposition (00:31:49)
12. Circuit Motifs (00:33:59)
13. Claim 3: Universality (00:34:55)
14. Interpretability as a Natural Science (00:39:37)
15. Closing Thoughts (00:42:49)
85 episodes
Partager
