Evaluation of the computational capabilities of a memristive random network (MN3) under the context of reservoir computing

Suarez, Laura E.; Kendall, Jack D.; Nino, Juan C.

doi:10.1016/j.neunet.2018.07.003

Cited by 12 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One such effort is the construction of physical reservoirs [138]. These include reservoirs built from analog circuits [6,77,126,166], field-programmable gate arrays (FPGA; [1,2,4,5,156]), very large-scale integration circuits (VLSI; [103,105,111]), memristive networks [13,41,68,71,123,134,161], and photonic or opto-electronic devices [66,67,73,148,149,165]. The architectures of these algorithms and systems, however, rarely take advantage of emerging understanding of connection patterns in biological networks.…”

Section: Discussionmentioning

confidence: 99%

Learning function from structure in neuromorphic networks

et al. 2021

View full text Add to dashboard Cite

The connection patterns of neural circuits in the brain form a complex network. Collective signaling within the network manifests as patterned neural activity, and is thought to support human cognition and adaptive behavior. Recent technological advances permit macro-scale reconstructions of biological brain networks. These maps, termed connectomes, display multiple non-random architectural features, including heavy-tailed degree distributions, segregated communities and a densely interconnected core. Yet, how computation and functional specialization emerge from network architecture remains unknown. Here we reconstruct human brain connectomes using in vivo diffusion-weighted imaging, and use reservoir computing to implement these connectomes as artificial neural networks. We then train these neuromorphic networks to learn a cognitive task. We show that biologically realistic neural architectures perform optimally when they display critical dynamics. We find that performance is driven by network topology, and that the modular organization of large-scale functional systems is computationally relevant. Throughout, we observe a prominent interaction between network structure and dynamics, such that the same underlying architecture can support a wide range of learning capacities across dynamical regimes. This work opens new opportunities to discover how the network organization of the brain optimizes cognitive capacity, conceptually bridging neuroscience and artificial intelligence.

show abstract

Section: Discussionmentioning

confidence: 99%

Learning function from structure in neuromorphic networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Here the goal is to exploit the rich dynamics of complex physical systems as information-processing devices. Physical substrates used for reservoirs are quite diverse: from analog circuits 101 – 104 , field programmable gate arrays 105 – 108 , photonic/opto-electronic devices 109 – 114 , spintronics 115 – 117 , quantum dynamics 118 , 119 , nanomaterials 120 – 126 , biological materials and organoids 127 – 133 , mechanics and robotics 134 – 136 , up to liquids or fluids 137 , 138 , and most recently, origami structures 139 . The development of physical reservoir systems has been accompanied by advances in more efficient and effective RC frameworks, for instance by including time delays 140 – 142 .…”

Section: Discussionmentioning

confidence: 99%

Connectome-based reservoir computing with the conn2res toolbox

Suárez,

Mihalik,

Milisav

et al. 2024

Nat Commun

View full text Add to dashboard Cite

The connection patterns of neural circuits form a complex network. How signaling in these circuits manifests as complex cognition and adaptive behaviour remains the central question in neuroscience. Concomitant advances in connectomics and artificial intelligence open fundamentally new opportunities to understand how connection patterns shape computational capacity in biological brain networks. Reservoir computing is a versatile paradigm that uses high-dimensional, nonlinear dynamical systems to perform computations and approximate cognitive functions. Here we present : an open-source Python toolbox for implementing biological neural networks as artificial neural networks. is modular, allowing arbitrary network architecture and dynamics to be imposed. The toolbox allows researchers to input connectomes reconstructed using multiple techniques, from tract tracing to noninvasive diffusion imaging, and to impose multiple dynamical systems, from spiking neurons to memristive dynamics. The versatility of the toolbox allows us to ask new questions at the confluence of neuroscience and artificial intelligence. By reconceptualizing function as computation, sets the stage for a more mechanistic understanding of structure-function relationships in brain networks.

show abstract

“…Here the goal is to exploit the rich dynamics of complex physical systems as information-processing devices. Physical substrates used for reservoirs are quite diverse: from analog circuits [131][132][133][134], field programmable gate arrays [135][136][137][138], photonic opto-electronic devices [139][140][141][142][143][144], spintronics [145][146][147], quantum dynamics [148,149], nanomaterials [150][151][152][153][154][155][156], biological materials and organoids [157][158][159][160][161][162], mechanics and robotics [163][164][165], up to liquids or fluids [166,167], and most recently, origami structures [168]. As physical reservoir computing becomes more popular, we envision the use of conn2res as a workbench to explore the effect of network interactions on the computational properties of physical reservoirs.…”

Section: Discussionmentioning

confidence: 99%

conn2res: A toolbox for connectome-based reservoir computing

Mišić

Suárez

Mihalik³

et al. 2023

Preprint

View full text Add to dashboard Cite

The connection patterns of neural circuits form a complex network. How signaling in these circuits manifests as complex cognition and adaptive behaviour remains the central question in neuroscience. Concomitant advances in connectomics and artificial intelligence open fundamentally new opportunities to understand how connection patterns shape computational capacity in biological brain networks. Reservoir computing is a versatile paradigm that uses nonlinear dynamics of high-dimensional dynamical systems to perform computations and approximate cognitive functions. Here we present conn2res: an open-source Python toolbox for implementing biological neural networks as artificial neural networks. conn2res is modular, allowing arbitrary architectures and arbitrary dynamics to be imposed. The toolbox allows researchers to input connectomes reconstructed using multiple techniques, from tract tracing to noninvasive diffusion imaging, and to impose multiple dynamical systems, from simple spiking neurons to memristive dynamics. The versatility of the conn2res toolbox allows us to ask new questions at the confluence of neuroscience and artificial intelligence. By reconceptualizing function as computation, conn2res sets the stage for a more mechanistic understanding of structure-function relationships in brain networks.

show abstract

Evaluation of the computational capabilities of a memristive random network (MN3) under the context of reservoir computing

Cited by 12 publications

References 36 publications

Learning function from structure in neuromorphic networks

Learning function from structure in neuromorphic networks

Connectome-based reservoir computing with the conn2res toolbox

conn2res: A toolbox for connectome-based reservoir computing

Contact Info

Product

Resources

About