Adaptive Mixtures of Local Experts.¶
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991). Adaptive Mixtures of Local Experts. Neural Computation, 3(1), 79-87.
Cited by¶
3 citations across 3 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Cognitive Flexibility
- The broader-repertoire-survives-disturbance finding from behavioral ecology transfers to ensemble and mixture-of-experts architectures in machine learning, where the gating-network problem is the structural twin of the foraging trigger problem.
This sourceIntroduces the mixture-of-experts architecture in which a gating network selects among specialized experts — the structural twin of repertoire-plus-trigger switching.
Supported in partVerified against the publisher's abstract
Its abstract establishes only that mixture-of-experts learning divides a task among separate networks; it says nothing about gating networks, behavioral ecology, or a cross-domain transfer.
“We present a new supervised learning procedure for systems composed of many separate networks, each of which learns to handle a subset of the complete set of training cases.”
- The broader-repertoire-survives-disturbance finding from behavioral ecology transfers to ensemble and mixture-of-experts architectures in machine learning, where the gating-network problem is the structural twin of the foraging trigger problem.
- Precision Weighting
- In weighted wisdom-of-crowds, contributions can scale with demonstrated accuracy; in mixture-of-experts and ensemble averaging, components are weighted by estimated reliability.
This sourceIntroduces mixture-of-experts, with the gating network a learned reliability-weighted allocator across experts.
Supported in partVerified against the publisher's abstract
The abstract confirms this work presents modular expert networks that split a task into subtasks, but it never states that experts are weighted by estimated reliability, so only the mixture-of-experts frame is supported.
“We present a new supervised learning procedure for systems composed of many separate networks, each of which learns to handle a subset of the complete set of training cases.”
- In weighted wisdom-of-crowds, contributions can scale with demonstrated accuracy; in mixture-of-experts and ensemble averaging, components are weighted by estimated reliability.
Mechanisms¶
- Local Model Ensemble with Gating
- This gating-network design is a mixture-of-experts architecture.
This sourceDefines an adaptive mixture architecture in which a gating network selects or weights local expert networks for each case.
- This gating-network design is a mixture-of-experts architecture.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 2 of 3 citations: 2 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:428dc13b0a05 · see in the full table