Neuromorphic computing hardware and neural architectures for robotics

Nanomaterials for Flexible Neuromorphics

The quest to imbue machines with intelligence akin to that of humans, through the development of adaptable neuromorphic devices and the creation of artificial neural systems, has long stood as a pivotal goal in both scientific inquiry and industrial advancement. Recent advancements in flexible neuromorphic electronics primarily rely on nanomaterials and polymers owing to their inherent uniformity, superior mechanical and electrical capabilities, and versatile functionalities. However, this field is still in its nascent stage, necessitating continuous efforts in materials innovation and device/system design. Therefore, it is imperative to conduct an extensive and comprehensive analysis to summarize current progress. This review highlights the advancements and applications of flexible neuromorphics, involving inorganic nanomaterials (zero-/one-/two-dimensional, and heterostructure), carbon-based nanomaterials such as carbon nanotubes (CNTs) and graphene, and polymers. Additionally, a comprehensive comparison and summary of the structural compositions, design strategies, key performance, and significant applications of these devices are provided. Furthermore, the challenges and future directions pertaining to materials/devices/systems associated with flexible neuromorphics are also addressed. The aim of this review is to shed light on the rapidly growing field of flexible neuromorphics, attract experts from diverse disciplines (e.g., electronics, materials science, neurobiology), and foster further innovation for its accelerated development.

IGZO/PVP Composite Nanofiber Neuromorphic Transistors with Optoelectronic Synapse Emulation and Reservoir Computing

Nanofiber neuromorphic transistors are regarded as promising candidates for mimicking brain-like learning and advancing high-performance computing. Composite nanofibers (CNFs) typically exhibit enhanced optoelectronic and mechanical properties. In this study, indium-gallium-zinc oxide (IGZO)/polyvinylpyrrolidone (PVP) CNFs were synthesized, and the neuromorphic transistor was integrated on both rigid and flexible substrates. The learning behavior, characterized by the transition from short-term plasticity (STP) to long-term plasticity, was achieved through photoelectric stimulation of the rigid neuromorphic transistor. The nonlinear STP was simulated by the flexible neuromorphic transistor through electrical pulses, matching effectively with a reservoir computing (RC) system. Hand gesture recognition with little energy consumption (49 pJ per reservoir state) and a maximum accuracy of 92.86% has been achieved by the RC system, proving the substantial potential of the IGZO/PVP CNF neuromorphic transistor for wearable intelligent processing tasks.

Toward a Brain-Neuromorphics Interface

Brain-computer interfaces (BCIs) that enable human-machine interaction have immense potential in restoring or augmenting human capabilities. Traditional BCIs are realized based on complementary metal-oxide-semiconductor (CMOS) technologies with complex, bulky, and low biocompatible circuits, and suffer with the low energy efficiency of the von Neumann architecture. The brain-neuromorphics interface (BNI) would offer a promising solution to advance the BCI technologies and shape the interactions with machineries. Neuromorphic devices and systems are able to provide substantial computation power with extremely high energy-efficiency by implementing in-materia computing such as in situ vector-matrix multiplication (VMM) and physical reservoir computing. Recent progresses on integrating neuromorphic components with sensing and/or actuating modules, give birth to the neuromorphic afferent nerve, efferent nerve, sensorimotor loop, and so on, which has advanced the technologies for future neurorobotics by achieving sophisticated sensorimotor capabilities as the biological system. With the development on the compact artificial spiking neuron and bioelectronic interfaces, the seamless communication between a BNI and a bioentity is reasonably expectable. In this review, the upcoming BNIs are profiled by introducing the brief history of neuromorphics, reviewing the recent progresses on related areas, and discussing the future advances and challenges that lie ahead.

Reconfigurable Neuromorphic Computing with 2D Material Heterostructures for Versatile Neural Information Processing

Reconfigurable neuromorphic computing holds promise for advancing energy-efficient neural network implementation and functional versatility. Previous work has focused on emulating specific neural functions rather than an integrated approach. We propose an all two-dimensional (2D) material-based heterostructure capable of performing multiple neuromorphic operations by reconfiguring output terminals in response to stimuli. Specifically, our device can synergistically emulate the key neural elements of the synapse, neuron, and dendrite, which play important and interrelated roles in information processing. Dendrites, the branches that receive and transmit presynaptic action potentials, possess the ability to nonlinearly integrate and filter incoming signals. The proposed heterostructure allows reconfiguration between different operation modes, demonstrating its potential for diverse computing tasks. As a proof of concept, we show that the device can perform basic Boolean logic functions. This highlights its applicability to complex neural-network-based information processing problems. Our integrated neuromorphic approach may advance the development of versatile, low-power neuromorphic hardware.

Gradient-free training of recurrent neural networks using random perturbations

Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter efficiency challenges. Backpropagation through time (BPTT), the prevailing method, extends the backpropagation (BP) algorithm by unrolling the RNN over time. However, this approach suffers from significant drawbacks, including the need to interleave forward and backward phases and store exact gradient information. Furthermore, BPTT has been shown to struggle to propagate gradient information for long sequences, leading to vanishing gradients. An alternative strategy to using gradient-based methods like BPTT involves stochastically approximating gradients through perturbation-based methods. This learning approach is exceptionally simple, necessitating only forward passes in the network and a global reinforcement signal as feedback. Despite its simplicity, the random nature of its updates typically leads to inefficient optimization, limiting its effectiveness in training neural networks. In this study, we present a new approach to perturbation-based learning in RNNs whose performance is competitive with BPTT, while maintaining the inherent advantages over gradient-based learning. To this end, we extend the recently introduced activity-based node perturbation (ANP) method to operate in the time domain, leading to more efficient learning and generalization. We subsequently conduct a range of experiments to validate our approach. Our results show similar performance, convergence time and scalability when compared to BPTT, strongly outperforming standard node perturbation and weight perturbation methods. These findings suggest that perturbation-based learning methods offer a versatile alternative to gradient-based methods for training RNNs which can be ideally suited for neuromorphic computing applications.

Bio-inspired multimodal learning with organic neuromorphic electronics for behavioral conditioning in robotics

Biological systems interact directly with the environment and learn by receiving multimodal feedback via sensory stimuli that shape the formation of internal neuronal representations. Drawing inspiration from biological concepts such as exploration and sensory processing that eventually lead to behavioral conditioning, we present a robotic system handling objects through multimodal learning. A small-scale organic neuromorphic circuit locally integrates and adaptively processes multimodal sensory stimuli, enabling the robot to interact intelligently with its surroundings. The real-time handling of sensory stimuli via low-voltage organic neuromorphic devices with synaptic functionality forms multimodal associative connections that lead to behavioral conditioning, and thus the robot learns to avoid potentially dangerous objects. This work demonstrates that adaptive neuro-inspired circuitry with multifunctional organic materials, can accommodate locally efficient bio-inspired learning for advancing intelligent robotics.

Firing feature-driven neural circuits with scalable memristive neurons for robotic obstacle avoidance

Neural circuits with specific structures and diverse neuronal firing features are the foundation for supporting intelligent tasks in biology and are regarded as the driver for catalyzing next-generation artificial intelligence. Emulating neural circuits in hardware underpins engineering highly efficient neuromorphic chips, however, implementing a firing features-driven functional neural circuit is still an open question. In this work, inspired by avoidance neural circuits of crickets, we construct a spiking feature-driven sensorimotor control neural circuit consisting of three memristive Hodgkin-Huxley neurons. The ascending neurons exhibit mixed tonic spiking and bursting features, which are used for encoding sensing input. Additionally, we innovatively introduce a selective communication scheme in biology to decode mixed firing features using two descending neurons. We proceed to integrate such a neural circuit with a robot for avoidance control and achieve lower latency than conventional platforms. These results provide a foundation for implementing real brain-like systems driven by firing features with memristive neurons and put constructing high-order intelligent machines on the agenda.

Fully neuromorphic vision and control for autonomous drone flight

Biological sensing and processing is asynchronous and sparse, leading to low-latency and energy-efficient perception and action. In robotics, neuromorphic hardware for event-based vision and spiking neural networks promises to exhibit similar characteristics. However, robotic implementations have been limited to basic tasks with low-dimensional sensory inputs and motor actions because of the restricted network size in current embedded neuromorphic processors and the difficulties of training spiking neural networks. Here, we present a fully neuromorphic vision-to-control pipeline for controlling a flying drone. Specifically, we trained a spiking neural network that accepts raw event-based camera data and outputs low-level control actions for performing autonomous vision-based flight. The vision part of the network, consisting of five layers and 28,800 neurons, maps incoming raw events to ego-motion estimates and was trained with self-supervised learning on real event data. The control part consists of a single decoding layer and was learned with an evolutionary algorithm in a drone simulator. Robotic experiments show a successful sim-to-real transfer of the fully learned neuromorphic pipeline. The drone could accurately control its ego-motion, allowing for hovering, landing, and maneuvering sideways-even while yawing at the same time. The neuromorphic pipeline runs on board on Intel's Loihi neuromorphic processor with an execution frequency of 200 hertz, consuming 0.94 watt of idle power and a mere additional 7 to 12 milliwatts when running the network. These results illustrate the potential of neuromorphic sensing and processing for enabling insect-sized intelligent robots.

An artificial visual neuron with multiplexed rate and time-to-first-spike coding

Human visual neurons rely on event-driven, energy-efficient spikes for communication, while silicon image sensors do not. The energy-budget mismatch between biological systems and machine vision technology has inspired the development of artificial visual neurons for use in spiking neural network (SNN). However, the lack of multiplexed data coding schemes reduces the ability of artificial visual neurons in SNN to emulate the visual perception ability of biological systems. Here, we present an artificial visual spiking neuron that enables rate and temporal fusion (RTF) coding of external visual information. The artificial neuron can code visual information at different spiking frequencies (rate coding) and enables precise and energy-efficient time-to-first-spike (TTFS) coding. This multiplexed sensory coding scheme could improve the computing capability and efficacy of artificial visual neurons. A hardware-based SNN with the RTF coding scheme exhibits good consistency with real-world ground truth data and achieves highly accurate steering and speed predictions for self-driving vehicles in complex conditions. The multiplexed RTF coding scheme demonstrates the feasibility of developing highly efficient spike-based neuromorphic hardware.

Flexible Organic Transistors for Biosensing: Devices and Applications

Flexible and stretchable biosensors can offer seamless and conformable biological-electronic interfaces for continuously acquiring high-fidelity signals, permitting numerous emerging applications. Organic thin film transistors (OTFTs) are ideal transducers for flexible and stretchable biosensing due to their soft nature, inherent amplification function, biocompatibility, ease of functionalization, low cost, and device diversity. In consideration of the rapid advances in flexible-OTFT-based biosensors and their broad applications, herein, a timely and comprehensive review is provided. It starts with a detailed introduction to the features of various OTFTs including organic field-effect transistors and organic electrochemical transistors, and the functionalization strategies for biosensing, with a highlight on the seminal work and up-to-date achievements. Then, the applications of flexible-OTFT-based biosensors in wearable, implantable, and portable electronics, as well as neuromorphic biointerfaces are detailed. Subsequently, special attention is paid to emerging stretchable organic transistors including planar and fibrous devices. The routes to impart stretchability, including structural engineering and material engineering, are discussed, and the implementations of stretchable organic transistors in e-skin and smart textiles are included. Finally, the remaining challenges and the future opportunities in this field are summarized.

A modular organic neuromorphic spiking circuit for retina-inspired sensory coding and neurotransmitter-mediated neural pathways

Signal communication mechanisms within the human body rely on the transmission and modulation of action potentials. Replicating the interdependent functions of receptors, neurons and synapses with organic artificial neurons and biohybrid synapses is an essential first step towards merging neuromorphic circuits and biological systems, crucial for computing at the biological interface. However, most organic neuromorphic systems are based on simple circuits which exhibit limited adaptability to both external and internal biological cues, and are restricted to emulate only specific the functions of an individual neuron/synapse. Here, we present a modular neuromorphic system which combines organic spiking neurons and biohybrid synapses to replicate a neural pathway. The spiking neuron mimics the sensory coding function of afferent neurons from light stimuli, while the neuromodulatory activity of interneurons is emulated by neurotransmitters-mediated biohybrid synapses. Combining these functions, we create a modular connection between multiple neurons to establish a pre-processing retinal pathway primitive.

Shaping high-performance wearable robots for human motor and sensory reconstruction and enhancement

Most wearable robots such as exoskeletons and prostheses can operate with dexterity, while wearers do not perceive them as part of their bodies. In this perspective, we contend that integrating environmental, physiological, and physical information through multi-modal fusion, incorporating human-in-the-loop control, utilizing neuromuscular interface, employing flexible electronics, and acquiring and processing human-robot information with biomechatronic chips, should all be leveraged towards building the next generation of wearable robots. These technologies could improve the embodiment of wearable robots. With optimizations in mechanical structure and clinical training, the next generation of wearable robots should better facilitate human motor and sensory reconstruction and enhancement.

Reconfigurable Cascaded Thermal Neuristors for Neuromorphic Computing

While the complementary metal-oxide semiconductor (CMOS) technology is the mainstream for the hardware implementation of neural networks, an alternative route is explored based on a new class of spiking oscillators called "thermal neuristors", which operate and interact solely via thermal processes. Utilizing the insulator-to-metal transition (IMT) in vanadium dioxide, a wide variety of reconfigurable electrical dynamics mirroring biological neurons is demonstrated. Notably, inhibitory functionality is achieved just in a single oxide device, and cascaded information flow is realized exclusively through thermal interactions. To elucidate the underlying mechanisms of the neuristors, a detailed theoretical model is developed, which accurately reflects the experimental results. This study establishes the foundation for scalable and energy-efficient thermal neural networks, fostering progress in brain-inspired computing.

Single Wavelength Operating Neuromorphic Device Based on a Graphene-Ferroelectric Transistor

As global data generation continues to rise, there is an increasing demand for revolutionary in-memory computing methodologies and efficient machine learning solutions. Despite recent progress in electrical and electro-optical simulations of machine learning devices, the all-optical nonthermal function remains challenging, with single wavelength operation still elusive. Here we report on an optical and monochromatic way of neuromorphic signal processing for brain-inspired functions, eliminating the need for electrical pulses. Multilevel synaptic potentiation-depression cycles are successfully achieved optically by leveraging photovoltaic charge generation and polarization within the photoferroelectric substrate interfaced with the graphene sensor. Furthermore, the demonstrated low-power prototype device is able to reproduce exact signal profile of brain tissues yet with more than 2 orders of magnitude faster response. The reported properties should trigger all-optical and low power artificial neuromorphic development based on photoferroelectric structures.

Reconfigurable Neuromorphic Computing: Materials, Devices, and Integration

Neuromorphic computing has been attracting ever-increasing attention due to superior energy efficiency, with great promise to promote the next wave of artificial general intelligence in the post-Moore era. Current approaches are, however, broadly designed for stationary and unitary assignments, thus encountering reluctant interconnections, power consumption, and data-intensive computing in that domain. Reconfigurable neuromorphic computing, an on-demand paradigm inspired by the inherent programmability of brain, can maximally reallocate finite resources to perform the proliferation of reproducibly brain-inspired functions, highlighting a disruptive framework for bridging the gap between different primitives. Although relevant research has flourished in diverse materials and devices with novel mechanisms and architectures, a precise overview remains blank and urgently desirable. Herein, the recent strides along this pursuit are systematically reviewed from material, device, and integration perspectives. At the material and device level, one comprehensively conclude the dominant mechanisms for reconfigurability, categorized into ion migration, carrier migration, phase transition, spintronics, and photonics. Integration-level developments for reconfigurable neuromorphic computing are also exhibited. Finally, a perspective on the future challenges for reconfigurable neuromorphic computing is discussed, definitely expanding its horizon for scientific communities.

Hybrid Life: Integrating biological, artificial, and cognitive systems

Artificial life is a research field studying what processes and properties define life, based on a multidisciplinary approach spanning the physical, natural, and computational sciences. Artificial life aims to foster a comprehensive study of life beyond "life as we know it" and toward "life as it could be," with theoretical, synthetic, and empirical models of the fundamental properties of living systems. While still a relatively young field, artificial life has flourished as an environment for researchers with different backgrounds, welcoming ideas, and contributions from a wide range of subjects. Hybrid Life brings our attention to some of the most recent developments within the artificial life community, rooted in more traditional artificial life studies but looking at new challenges emerging from interactions with other fields. Hybrid Life aims to cover studies that can lead to an understanding, from first principles, of what systems are and how biological and artificial systems can interact and integrate to form new kinds of hybrid (living) systems, individuals, and societies. To do so, it focuses on three complementary perspectives: theories of systems and agents, hybrid augmentation, and hybrid interaction. Theories of systems and agents are used to define systems, how they differ (e.g., biological or artificial, autonomous, or nonautonomous), and how multiple systems relate in order to form new hybrid systems. Hybrid augmentation focuses on implementations of systems so tightly connected that they act as a single, integrated one. Hybrid interaction is centered around interactions within a heterogeneous group of distinct living and nonliving systems. After discussing some of the major sources of inspiration for these themes, we will focus on an overview of the works that appeared in Hybrid Life special sessions, hosted by the annual Artificial Life Conference between 2018 and 2022. This article is categorized under: Neuroscience > Cognition Philosophy > Artificial Intelligence Computer Science and Robotics > Robotics.

From Brain Models to Robotic Embodied Cognition: How Does Biological Plausibility Inform Neuromorphic Systems?

We examine the challenging "marriage" between computational efficiency and biological plausibility-A crucial node in the domain of spiking neural networks at the intersection of neuroscience, artificial intelligence, and robotics. Through a transdisciplinary review, we retrace the historical and most recent constraining influences that these parallel fields have exerted on descriptive analysis of the brain, construction of predictive brain models, and ultimately, the embodiment of neural networks in an enacted robotic agent. We study models of Spiking Neural Networks (SNN) as the central means enabling autonomous and intelligent behaviors in biological systems. We then provide a critical comparison of the available hardware and software to emulate SNNs for investigating biological entities and their application on artificial systems. Neuromorphics is identified as a promising tool to embody SNNs in real physical systems and different neuromorphic chips are compared. The concepts required for describing SNNs are dissected and contextualized in the new no man's land between cognitive neuroscience and artificial intelligence. Although there are recent reviews on the application of neuromorphic computing in various modules of the guidance, navigation, and control of robotic systems, the focus of this paper is more on closing the cognition loop in SNN-embodied robotics. We argue that biologically viable spiking neuronal models used for electroencephalogram signals are excellent candidates for furthering our knowledge of the explainability of SNNs. We complete our survey by reviewing different robotic modules that can benefit from neuromorphic hardware, e.g., perception (with a focus on vision), localization, and cognition. We conclude that the tradeoff between symbolic computational power and biological plausibility of hardware can be best addressed by neuromorphics, whose presence in neurorobotics provides an accountable empirical testbench for investigating synthetic and natural embodied cognition. We argue this is where both theoretical and empirical future work should converge in multidisciplinary efforts involving neuroscience, artificial intelligence, and robotics.

Neuromorphic sequence learning with an event camera on routes through vegetation

For many robotics applications, it is desirable to have relatively low-power and efficient onboard solutions. We took inspiration from insects, such as ants, that are capable of learning and following routes in complex natural environments using relatively constrained sensory and neural systems. Such capabilities are particularly relevant to applications such as agricultural robotics, where visual navigation through dense vegetation remains a challenging task. In this scenario, a route is likely to have high self-similarity and be subject to changing lighting conditions and motion over uneven terrain, and the effects of wind on leaves increase the variability of the input. We used a bioinspired event camera on a terrestrial robot to collect visual sequences along routes in natural outdoor environments and applied a neural algorithm for spatiotemporal memory that is closely based on a known neural circuit in the insect brain. We show that this method is plausible to support route recognition for visual navigation and more robust than SeqSLAM when evaluated on repeated runs on the same route or routes with small lateral offsets. By encoding memory in a spiking neural network running on a neuromorphic computer, our model can evaluate visual familiarity in real time from event camera footage.

Hardware-Software Partitioning for Real-Time Object Detection Using Dynamic Parameter Optimization

Computer vision algorithms implementations, especially for real-time applications, are present in a variety of devices that we are currently using (from smartphones or automotive applications to monitoring/security applications) and pose specific challenges, memory bandwidth or energy consumption (e.g., for mobility) being the most notable ones. This paper aims at providing a solution to improve the overall quality of real-time object detection computer vision algorithms using a hybrid hardware-software implementation. To this end, we explore the methods for a proper allocation of algorithm components towards hardware (as IP Cores) and the interfacing between hardware and software. Addressing specific design constraints, the relationship between the above components allows embedded artificial intelligence to select the operating hardware blocks (IP cores)-in the configuration phase-and to dynamically change the parameters of the aggregated hardware resources-in the instantiation phase, similar to the concretization of a class into a software object. The conclusions show the benefits of using hybrid hardware-software implementations, as well as major gains from using IP Cores, managed by artificial intelligence, for an object detection use-case, implemented on a FPGA demonstrator built around a Xilinx Zynq-7000 SoC Mini-ITX sub-system.

Brain-inspired multimodal hybrid neural network for robot place recognition

Place recognition is an essential spatial intelligence capability for robots to understand and navigate the world. However, recognizing places in natural environments remains a challenging task for robots because of resource limitations and changing environments. In contrast, humans and animals can robustly and efficiently recognize hundreds of thousands of places in different conditions. Here, we report a brain-inspired general place recognition system, dubbed NeuroGPR, that enables robots to recognize places by mimicking the neural mechanism of multimodal sensing, encoding, and computing through a continuum of space and time. Our system consists of a multimodal hybrid neural network (MHNN) that encodes and integrates multimodal cues from both conventional and neuromorphic sensors. Specifically, to encode different sensory cues, we built various neural networks of spatial view cells, place cells, head direction cells, and time cells. To integrate these cues, we designed a multiscale liquid state machine that can process and fuse multimodal information effectively and asynchronously using diverse neuronal dynamics and bioinspired inhibitory circuits. We deployed the MHNN on Tianjic, a hybrid neuromorphic chip, and integrated it into a quadruped robot. Our results show that NeuroGPR achieves better performance compared with conventional and existing biologically inspired approaches, exhibiting robustness to diverse environmental uncertainty, including perceptual aliasing, motion blur, light, or weather changes. Running NeuroGPR as an overall multi-neural network workload on Tianjic showcases its advantages with 10.5 times lower latency and 43.6% lower power consumption than the commonly used mobile robot processor Jetson Xavier NX.

Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities

Spiking neural networks (SNNs) are subjects of a topic that is gaining more and more interest nowadays. They more closely resemble actual neural networks in the brain than their second-generation counterparts, artificial neural networks (ANNs). SNNs have the potential to be more energy efficient than ANNs on event-driven neuromorphic hardware. This can yield drastic maintenance cost reduction for neural network models, as the energy consumption would be much lower in comparison to regular deep learning models hosted in the cloud today. However, such hardware is still not yet widely available. On standard computer architectures consisting mainly of central processing units (CPUs) and graphics processing units (GPUs) ANNs, due to simpler models of neurons and simpler models of connections between neurons, have the upper hand in terms of execution speed. In general, they also win in terms of learning algorithms, as SNNs do not reach the same levels of performance as their second-generation counterparts in typical machine learning benchmark tasks, such as classification. In this paper, we review existing learning algorithms for spiking neural networks, divide them into categories by type, and assess their computational complexity.

Applications of Graphene in Five Senses, Nervous System, and Artificial Muscles

Graphene remains of great interest in biomedical applications because of biocompatibility. Diseases relating to human senses interfere with life satisfaction and happiness. Therefore, the restoration by artificial organs or sensory devices may bring a bright future by the recovery of senses in patients. In this review, we update the most recent progress in graphene based sensors for mimicking human senses such as artificial retina for image sensors, artificial eardrums, gas sensors, chemical sensors, and tactile sensors. The brain-like processors are discussed based on conventional transistors as well as memristor related neuromorphic computing. The brain-machine interface is introduced for providing a single pathway. Besides, the artificial muscles based on graphene are summarized in the means of actuators in order to react to the physical world. Future opportunities remain for elevating the performances of human-like sensors and their clinical applications.

Implementation of Kalman Filtering with Spiking Neural Networks

A Kalman filter can be used to fill space-state reconstruction dynamics based on knowledge of a system and partial measurements. However, its performance relies on accurate modeling of the system dynamics and a proper characterization of the uncertainties, which can be hard to obtain in real-life scenarios. In this work, we explore how the values of a Kalman gain matrix can be estimated by using spiking neural networks through a combination of biologically plausible neuron models with spike-time-dependent plasticity learning algorithms. The performance of proposed neural architecture is verified with simulations of some representative nonlinear systems, which show promising results. This approach traces a path for its implementation in neuromorphic analog hardware that can learn and reconstruct partial and changing dynamics of a system without the massive power consumption that is typically needed in a Von Neumann-based computer architecture.