Back to Search
Start Over
Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented Networks.
- Source :
-
IEEE transactions on neural networks and learning systems [IEEE Trans Neural Netw Learn Syst] 2023 Dec; Vol. 34 (12), pp. 10993-10998. Date of Electronic Publication: 2023 Nov 30. - Publication Year :
- 2023
-
Abstract
- Memory-augmented neural networks enhance a neural network with an external key-value (KV) memory whose complexity is typically dominated by the number of support vectors in the key memory. We propose a generalized KV memory that decouples its dimension from the number of support vectors by introducing a free parameter that can arbitrarily add or remove redundancy to the key memory representation. In effect, it provides an additional degree of freedom to flexibly control the tradeoff between robustness and the resources required to store and compute the generalized KV memory. This is particularly useful for realizing the key memory on in-memory computing hardware where it exploits nonideal, but extremely efficient nonvolatile memory devices for dense storage and computation. Experimental results show that adapting this parameter on demand effectively mitigates up to 44% nonidealities, at equal accuracy and number of devices, without any need for neural network retraining.
Details
- Language :
- English
- ISSN :
- 2162-2388
- Volume :
- 34
- Issue :
- 12
- Database :
- MEDLINE
- Journal :
- IEEE transactions on neural networks and learning systems
- Publication Type :
- Academic Journal
- Accession number :
- 35333724
- Full Text :
- https://doi.org/10.1109/TNNLS.2022.3159445