Towards replicated algorithms

• URL: http://arxiv.org/abs/2304.13524v1
• Date: Fri, 31 Mar 2023 08:56:54 GMT
• Title: Towards replicated algorithms
• Authors: Iztok Fister Jr. and Iztok Fister
• Abstract summary: The paper introduces the so-called replicated algorithms, inspired by the concept of developing a human brain. Similar to the human brain, where the process of thinking is strongly parallel, replicated algorithms are also capable of replicating themselves and solving problems in parallel.
• Score: 2.535671322516818
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The main deficiency of the algorithms running on digital computers nowadays is their inability to change themselves during the execution. In line with this, the paper introduces the so-called replicated algorithms, inspired by the concept of developing a human brain. Similar to the human brain, where the process of thinking is strongly parallel, replicated algorithms, incorporated into a population, are also capable of replicating themselves and solving problems in parallel. They operate as a model for mapping the known input to a known output. In our preliminary study, these algorithms are built as sequences of arithmetic operators, applied for calculating arithmetic expressions, while their behavior showed that they can operate in the condition of open-ended evolution.

Related papers

• Discrete Neural Algorithmic Reasoning [18.497863598167257]
  We propose to force neural reasoners to maintain the execution trajectory as a combination of finite predefined states. trained with supervision on the algorithm's state transitions, such models are able to perfectly align with the original algorithm.
  arXiv  Detail & Related papers  (2024-02-18T16:03:04Z)
• The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks [59.26515696183751]
  We show that algorithm discovery in neural networks is sometimes more complex. We show that even simple learning problems can admit a surprising diversity of solutions.
  arXiv  Detail & Related papers  (2023-06-30T17:59:13Z)
• Bio-inspired Machine Learning: programmed death and replication [0.0]
  We develop machine learning algorithms for adding neurons to the system and removing neurons from the system. We argue that the programmed death algorithm can be used for compression of neural networks and the replication algorithm can be used for improving performance of the already trained neural networks. The computational advantages of the bio-inspired algorithms are demonstrated by training feedforward neural networks on the MNIST dataset.
  arXiv  Detail & Related papers  (2022-06-30T10:44:12Z)
• Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems [120.297940190903]
  Recent progress in AI has resulted from the use of limited forms of neurocompositional computing. New, deeper forms of neurocompositional computing create AI systems that are more robust, accurate, and comprehensible.
  arXiv  Detail & Related papers  (2022-05-02T18:00:10Z)
• End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking [52.05847268235338]
  We show how machine learning systems can perform logical extrapolation without overthinking problems. We propose a recall architecture that keeps an explicit copy of the problem instance in memory so that it cannot be forgotten. We also employ a progressive training routine that prevents the model from learning behaviors that are specific to number and instead pushes it to learn behaviors that can be repeated indefinitely.
  arXiv  Detail & Related papers  (2022-02-11T18:43:28Z)
• Towards algorithm-free physical equilibrium model of computing [0.0]
  A new model of computing is proposed to replace the sequential paradigm of algorithms with inherent parallelism of physical processes. We construct physical systems whose equilibrium states correspond to the desired solutions and let them evolve to search for the solutions. The main requirements of the model are identified and quantum circuits are proposed for its potential implementation.
  arXiv  Detail & Related papers  (2021-11-30T09:48:39Z)
• Unsupervised Behaviour Discovery with Quality-Diversity Optimisation [1.0152838128195467]
  Quality-Diversity algorithms refer to a class of evolutionary algorithms designed to find a collection of diverse and high-performing solutions to a given problem. In robotics, such algorithms can be used for generating a collection of controllers covering most of the possible behaviours of a robot. In this paper, we introduce: Autonomous Robots Realising their Abilities, an algorithm that uses a dimensionality reduction technique to automatically learn behavioural descriptors.
  arXiv  Detail & Related papers  (2021-06-10T10:40:18Z)
• Neural Algorithmic Reasoning [11.566653801306844]
  We argue that algorithms possess fundamentally different qualities to deep learning methods. By representing elements in a continuous space of learnt algorithms, neural networks are able to adapt known algorithms more closely to real-world problems.
  arXiv  Detail & Related papers  (2021-05-06T15:33:57Z)
• Evolving Reinforcement Learning Algorithms [186.62294652057062]
  We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
  arXiv  Detail & Related papers  (2021-01-08T18:55:07Z)
• Coded Distributed Computing with Partial Recovery [56.08535873173518]
  We introduce a novel coded matrix-vector multiplication scheme, called coded computation with partial recovery (CCPR) CCPR reduces both the computation time and the decoding complexity by allowing a trade-off between the accuracy and the speed of computation. We then extend this approach to distributed implementation of more general computation tasks by proposing a coded communication scheme with partial recovery.
  arXiv  Detail & Related papers  (2020-07-04T21:34:49Z)
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey [53.429871539789445]
  Spiking Neural Networks are cognitive algorithms mimicking neuron and synapse operational principles. We present the state of the art of hardware implementations of spiking neural networks. We discuss the strategies employed to leverage the characteristics of these event-driven algorithms at the hardware level.
  arXiv  Detail & Related papers  (2020-05-04T13:24:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.