Name
Abstract | ||
|---|---|---|
We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of models can be effectively stored within a single parameter instance. Furthermore, each of these models can undergo thousands of training steps without significantly interfering with other models within the superposition. This approach may be viewed as the online complement of compression: rather than reducing the size of a network after training, we make use of the unrealized capacity of a network during training. |
Year | Venue | Keywords |
|---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | neural networks |
Field | DocType | Volume |
Superposition principle,Algorithm,Artificial intelligence,Artificial neural network,Mathematics,Machine learning,Multiple Models | Journal | 32 |
ISSN | Citations | PageRank |
1049-5258 | 3 | 0.42 |
References | Authors | |
11 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Brian Cheung | 1 | 40 | 3.16 |
| Alex Terekhov | 2 | 3 | 0.42 |
| Yubei Chen | 3 | 16 | 2.74 |
| Pulkit Agrawal | 4 | 627 | 24.55 |
| Bruno A. Olshausen | 5 | 493 | 66.79 |
| Terekhov, Alexander | 6 | 3 | 0.42 |