Corpus ID: 195317051

Neural Stored-program Memory

  title={Neural Stored-program Memory},
  author={Hung Le and T. Tran and S. Venkatesh},
  • Hung Le, T. Tran, S. Venkatesh
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • 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
    8 Citations
    Neurocoder: Learning General-Purpose Computation Using Stored Neural Programs
    • PDF
    Distributed Memory based Self-Supervised Differentiable Neural Computer
    • PDF
    Self-Attentive Associative Memory
    • 4
    • PDF
    Self-Assttentive Associative Memory
    Neural Status Registers
    • 2
    • PDF


    Hybrid computing using a neural network with dynamic external memory
    • 924
    • Highly Influential
    • PDF
    Learning to Remember More with Less Memorization
    • 14
    • PDF
    Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes
    • 100
    • PDF
    Gated Fast Weights for On-The-Fly Neural Program Generation
    • 15
    • PDF
    Neural Turing Machines
    • 1,356
    • Highly Influential
    • PDF
    Using Fast Weights to Attend to the Recent Past
    • 117
    • PDF
    On the Computational Power of Neural Nets
    • 765
    End-To-End Memory Networks
    • 1,629
    • PDF
    The Dynamics of Discrete-Time Computation, with Application to Recurrent Neural Networks and Finite State Machine Extraction
    • M. Casey
    • Computer Science, Medicine
    • Neural Computation
    • 1996
    • 204
    Dual Memory Neural Computer for Asynchronous Two-view Sequential Learning
    • 21
    • PDF