Neural Stored-program Memory
@article{Le2020NeuralSM, title={Neural Stored-program Memory}, author={Hung Le and T. Tran and S. Venkatesh}, journal={ArXiv}, year={2020}, volume={abs/1906.08862} }
Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern computer architectures. The proposed model, dubbed Neural Stored-program Memory, augments current memory-augmented neural networks, creating differentiable machines that can… CONTINUE READING
Supplemental Code
Figures, Tables, and Topics from this paper
8 Citations
Neurocoder: Learning General-Purpose Computation Using Stored Neural Programs
- Computer Science
- ArXiv
- 2020
- PDF
Distributed Memory based Self-Supervised Differentiable Neural Computer
- Computer Science, Mathematics
- ArXiv
- 2020
- PDF
Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack
- Computer Science
- ArXiv
- 2020
- 1
- PDF
Provably Stable Interpretable Encodings of Context Free Grammars in RNNs with a Differentiable Stack
- Computer Science, Mathematics
- ArXiv
- 2020
- 1
- PDF
References
SHOWING 1-10 OF 37 REFERENCES
Hybrid computing using a neural network with dynamic external memory
- Computer Science, Medicine
- Nature
- 2016
- 924
- Highly Influential
- PDF
The Dynamics of Discrete-Time Computation, with Application to Recurrent Neural Networks and Finite State Machine Extraction
- Computer Science, Medicine
- Neural Computation
- 1996
- 204
Dual Memory Neural Computer for Asynchronous Two-view Sequential Learning
- Computer Science, Mathematics
- KDD
- 2018
- 21
- PDF