Learning without neurons in physical systems

Stern, Menachem; Murugan, Arvind

doi:10.48550/arxiv.2206.05831

Cited by 4 publications

(8 citation statements)

References 111 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the principles of learning systems can be very simple, and spontaneous "physical learning" can be readily demonstrated in various kinds of physical systems (Stern and Murugan 2022). These include mechanical, material, molecular and chemical systems, as well as electrical (Kim, Gaba et al 2012, McGregor, Vasas et al 2012, Stern, Pinson and Murugan 2020, Stern, Hexner et al 2021, Wright, Onodera et al , Parsa, Wang et al 2022, Stern and Murugan 2022, Venkatesan and Williams 2022. Although the details vary, the underlying principle is the differential 'accommodation' of system structures to forces acting on them.…”

Section: Physical Learning and Physical Optimisationmentioning

confidence: 99%

Natural Induction: Spontaneous adaptive organisation without natural selection

Buckley,

Lewens,

Levin

et al. 2024

Preprint

View full text Add to dashboard Cite

Evolution by natural selection is believed to be the only possible source of spontaneous adaptive organisation in the natural world. This places strict limits on the kinds of systems that can exhibit adaptation spontaneously, i.e. without design. Physical systems can show some properties relevant to adaptation without natural selection or design. 1) The relaxation, or local energy minimisation, of a physical system constitutes a natural form of optimisation insomuch as it finds locally optimal solutions to the frustrated forces acting on it or between its components. 2) When internal structure 'gives way' or accommodates to a pattern of forcing on a system this constitutes learning insomuch as it can store, recall and generalise past configurations. Both these effects are quite natural and general, but in themselves insufficient to constitute non-trivial adaptation. However, here we show that the recurrent interaction of physical optimisation and physical learning together results in significant spontaneous adaptive organisation. We call this adaptation by natural induction. The effect occurs in dynamical systems described by a network of viscoelastic connections subject to occasional disturbances. When the internal structure of such a system accommodates slowly across many disturbances and relaxations, it spontaneously learns to preferentially visit solutions of increasingly greater quality (exceptionally low energy). We show that adaptation by natural induction thus produces network organisations that improve problem-solving competency with experience. We note that the conditions for adaptation by natural induction, and its adaptive competency, are different from those of natural selection. We therefore suggest that natural selection is not the only possible source of spontaneous adaptive organisation in the natural world.

show abstract

Section: Physical Learning and Physical Optimisationmentioning

confidence: 99%

Natural Induction: Spontaneous adaptive organisation without natural selection

Buckley,

Lewens,

Levin

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Pattern recognition has been implemented in a variety of analog classical systems ranging from molecular self-assembly to elastic networks [55][56][57][58][59][60][61][62] . It is interesting to ask whether quantum systems possesses similar power.…”

Section: A Pattern Recognitionmentioning

confidence: 99%

Many-body localized hidden Born machine

Zhong¹,

Gao²,

Yelin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Born Machines are quantum-inspired generative models that leverage the probabilistic nature of quantum states. Here, we present a new architecture called many-body localized (MBL) hidden Born machine that uses both MBL dynamics and hidden units as learning resources. We theoretically prove that MBL Born machines possess more expressive power than classical models, and the introduction of hidden units boosts its learning power. We numerically demonstrate that the MBL hidden Born machine is capable of learning a toy version of MNIST handwritten digits, quantum data obtained from quantum many-body states, and non-local parity data. In order to understand the mechanism behind learning, we track physical quantities such as von Neumann entanglement entropy and Hamming distance during learning, and compare the learning outcomes in the MBL, thermal, and Anderson localized phases. We show that the superior learning power of the MBL phase relies importantly on both localization and interaction. Our architecture and algorithm provide novel strategies of utilizing quantum many-body systems as learning resources, and reveal a powerful connection between disorder, interaction, and learning in quantum many-body systems.

show abstract

“…The principles of distributed cognition familiar in artificial neural networks can be implemented by any network of signals and non-linear responses to suitably weighted inputs (Evans et al, 2022; Stern and Murugan, 2022; Watson et al, 2016). Gene-regulation networks, ecological networks and social networks can all compute in the same sense as neural networks if the connections are suitably arranged (Biswas et al, 2021; Davies et al, 2011; Herrera-Delgado et al, 2018; Power et al, 2015; Szabó et al, 2012; Tareen and Kinney, 2020; Watson et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

The collective intelligence of evolution and development

Watson

Levin

2023

Collective Intelligence

View full text Add to dashboard Cite

Collective intelligence and individual intelligence are usually considered to be fundamentally different. Individual intelligence is uncontroversial. It occurs in organisms with special neural machinery, evolved by natural selection to enable cognitive and learning functions that serve the fitness benefit of the organism, and then trained through lifetime experience to maximise individual rewards. Whilst the mechanisms of individual intelligence are not fully understood, good models exist for many aspects of individual cognition and learning. Collective intelligence, in contrast, is a much more ambiguous idea. What exactly constitutes collective intelligence is often vague, and the mechanisms that might enable it are frequently domain-specific. These cannot be mechanisms selected specifically for the purpose of collective intelligence because collectives are not (except in special circumstances) evolutionary units, and it is not clear that collectives can learn the way individual intelligences do since they are not a singular locus of rewards and benefits. Here, we use examples from evolution and developmental morphogenesis to argue that these apparent distinctions are not as categorical as they appear. Breaking down such distinctions enables us to borrow from and expand existing models of individual cognition and learning as a framework for collective intelligence, in particular connectionist models familiar in the context of neural networks. We discuss how specific features of these models inform the necessary and sufficient conditions for collective intelligence, and identify current knowledge gaps as opportunities for future research.

show abstract

Learning without neurons in physical systems

Cited by 4 publications

References 111 publications

Natural Induction: Spontaneous adaptive organisation without natural selection

Natural Induction: Spontaneous adaptive organisation without natural selection

Many-body localized hidden Born machine

The collective intelligence of evolution and development

Contact Info

Product

Resources

About