CircuitTree: Composing Circuits into A Syllable Transcriber
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:CircuitTree: Composing Circuits into A Syllable Transcriber
Abstract:The goal of circuit discovery is to decompose a monolithic neural network into tiny modular subnetworks which are interpretable in the sense that each does an identifiable subtask. We develop a practical method for composing arbitrarily many circuits into a single model. We propose a greedy, density-scaled composition algorithm that overcomes limitations of previous attempts to compose circuits by naive union, then generalize it to $N$ circuits via CircuitTree, a new data structure built on a $\Theta(N\log N)$ tree-compose schedule. We compose circuits pruned from HuBERT for classifying individual phonemes into a syllable classifier, a capability none of the 39 phoneme circuits has individually. Chaining CircuitTrees into a hierarchy-of-circuits pipeline, we transcribe open syllables at 64.8\% accuracy, within 1.2 points of a 66.0\% ceiling that shares no circuitry at all, with 99.5\% of circuit components shared.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Sound (cs.SD) |
| Cite as: | arXiv:2610.12520 [cs.LG] |
| (or arXiv:2610.12520v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12520
arXiv-issued DOI via DataCite
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
Additional Features
Current browse context:
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Algebraic Integer Quantization for Machine Learning Applications
Oct 12
-
Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights
Oct 12
-
GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer
Oct 12
-
CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration
Oct 12
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.