The Function-Representation Model of Computation
Not on the map. Why?
Abstract (arXiv)
Cognitive Architectures are the forefront of the research into developing an artificial cognition. However, they approach the problem from a separated memory and program model of computation. This model of computation poses a fundamental problem: the knowledge retrieval heuristic. In this paper we propose to solve this problem by using a novel model of computation, one where memory and program are merged: the Function-Representation. This model of computation involves defining a generic Function-Representation and instantiating multiple instances of it. In this paper we explore the potential of this novel model of computation through mathematical definitions and proofs. We also explore the kind of functions a Function-Representation can implement, and present different ways to organise multiple instances of a Function-Representation.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 50 references that are in the map. First posted on arXiv 10 Oct 2024.
Builds on
8 of 50 references.
References · 8
- 2022Survey of Hallucination in Natural Language Generationcited by 2,056
- 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
- 2021Shaking the foundations: delusions in sequence models for interaction and controlcited by 61
- 2015A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extractioncited by 46
- 2015Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortexcited by 44
- 2019TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learningcited by 42
- 2023On the Kolmogorov neural networkscited by 19
- 2024From Manifestations to Cognitive Architectures: a Scalable Frameworkcited by 4
Built on by
Not cited yet.