Abstract Radar sensors are a corner stone of autonomous driving, offering reliable perception under adverse weather and lighting conditions. However, the increasing resolution of modern automotive radar systems generates large data volumes that must be processed in real time, imposing significant computational and energy demands. This challenge is particularly acute in energy-constrained platforms such as electric vehicles and embedded devices, where power efficiency is critical. Neuromorphic computing offers a promising alternative by emulating the brain's event-driven and energy-efficient information processing. In this work, we extend existing resonate-and-fire neuron models, called spiking neural resonators (SpiNRs), into the Doppler domain to enable velocity estimation. We integrate SpiNR with a spiking Ordered Statistics Constant False Alarm Rate (OS-CFAR) algorithm to realize a full neuromorphic peak detection. Crucially, we introduce a novel activity-gated sparsity mechanism that dynamically deactivates inactive resonators, substantially reducing energy consumption while preserving estimation fidelity. All neuromorphic algorithms are implemented on Intel's Loihi 2 neuromorphic processor, which allows us to exploit event-driven computation and benchmark against conventional digital implementations under realistic hardware constraints. Evaluation against the conventional Fast Fourier Transform and classical OS-CFAR pipeline demonstrates that SpinR achieves competitive accuracy in range-velocity estimation. The proposed activity-gated sparsity mechanism yields additional energy savings and removes the need for a separate peak detection stage, further simplifying the processing chain. These findings highlight the potential of neuromorphic radar processing as a power-efficient alternative to conventional methods and underscore the importance of developing next-generation neuromorphic substrates optimized for embedded signal processing.

Abstract Despite recent progress in training spiking neural networks (SNNs) for classification, their application to continuous motor control remains limited. 
Here, we demonstrate that fully spiking architectures can be trained end-to-end to control robotic arms with multiple degrees of freedom in continuous environments. 
Our predictive-control framework combines Leaky Integrate-and-Fire dynamics with surrogate gradients, jointly optimizing a forward model for dynamics prediction and a policy network for goal-directed action. 
We evaluate this approach on both a planar 2D reaching task and a simulated 6-DOF Franka Emika Panda robot with torque control. 
In direct comparison to non-spiking recurrent baselines trained under the same predictive-control pipeline, the proposed SNN achieves comparable task performance while using substantially fewer parameters.
An extensive ablation study highlights the role of initialization, learnable time constants, adaptive thresholds, and latent-space compression as key contributors to stable training and effective control. 
Together, these findings establish spiking neural networks as a viable and scalable substrate for high-dimensional continuous control, while emphasizing the importance of principled architectural and training design.

Abstract Recent efforts to improve the efficiency of neuromorphic and machine learning systems have centred on developing of specialised hardware for neural networks. These systems typically feature architectures that go beyond the von Neumann model employed in general-purpose hardware such as GPUs, offering potential efficiency and performance gains. However, neural networks developed for specialised hardware must consider its specific characteristics. This requires novel training algorithms and accurate hardware models, since they cannot be abstracted as a general-purpose computing platform. In this work, we present a bottom-up approach to training neural networks for hardware-based spiking neurons and synapses, built using ferroelectric capacitors (FeCAPs) and resistive random-access memories (RRAMs), respectively. Unlike the common approach of designing hardware to fit abstract neuron or synapse models, we start with compact models of the physical device to model the computational primitives. Based on these models, we have developed a training algorithm (BRUNO) that can reliably train the networks, even when applying hardware limitations, such as stochasticity or low bit precision. We analyse and compare BRUNO with Backpropagation Through Time. We test it on different spatio-temporal datasets. First on a music prediction dataset, where a network composed of ferroelectric leaky integrate-and-fire (FeLIF) neurons is used to predict at each time step the next musical note that should be played. The second dataset consists on the classification of the Braille letters using a network composed of quantised RRAM synapses and FeLIF neurons. The performance of this network is then compared with that of networks composed of LIF neurons. Experimental results show the potential advantages of using BRUNO by reducing the time and memory required to detect spatio-temporal patterns with quantised synapses.

Abstract It has long been realized that neuromorphic hardware offers benefits for the domain of robotics such as low energy, low latency, as well as unique methods of learning. In aiming for more complex tasks, especially those incorporating multimodal data, one hurdle continuing to prevent their realization is an inability to orchestrate multiple networks on neuromorphic hardware without resorting to off-chip process management logic. To address this, we show a first example of a pipeline for vision-based robot control in which numerous complex networks can be run entirely on hardware via the use of a spiking neural state machine for process orchestration. The pipeline is validated on the Intel Loihi 2 research chip. We show that all components can run concurrently on-chip in the milliwatt regime at latencies competitive with the state-of-theart. An equivalent network on simulated hardware is shown to accomplish robotic arm plug insertion in simulation, and the core elements of the pipeline are additionally tested on a real robotic arm.

Abstract Neuromorphic vision made significant progress in recent years, thanks to the natural match between spiking neural networks and event data in terms of biological inspiration, energy savings, latency and memory use for dynamic visual data processing. However, optimising its energy requirements still remains a challenge within the community, especially for embedded applications. One solution may reside in preprocessing events to optimise data quantity thus lowering the energy cost on neuromorphic hardware, proportional to the number of synaptic operations. To this end, we extend an end-to-end neuromorphic line detection mechanism to introduce line-based event data preprocessing. Our results demonstrate on three benchmark event-based datasets that preprocessing leads to an advantageous trade-off between energy consumption and classification performance. Depending on the line-based preprocessing strategy and the complexity of the classification task, we show that one can maintain or increase the classification accuracy while significantly reducing the theoretical energy consumption. Our approach systematically leads to a significant improvement of the neuromorphic classification efficiency, thus laying the groundwork towards a more frugal neuromorphic computer vision thanks to event preprocessing.

Abstract Recurrent spiking neural networks (RSNNs) can be implemented very efficiently in neuromorphic systems. Nevertheless, training of these models with powerful gradient-based learning algorithms is mostly performed on standard digital hardware using Backpropagation through time (BPTT). However, BPTT has substantial limitations. It does not permit online training and its memory consumption scales linearly with the number of computation steps. In contrast, learning methods using forward propagation of gradients operate in an online manner with a memory consumption independent of the number of time steps. These methods enable SNNs to learn from continuous, infinite-length input sequences. In addition, approximate forward propagation algorithms have been developed that can be implemented on neuromorphic hardware. Yet, slow execution speed on conventional hardware as well as inferior performance has hindered their widespread application. In this work, we introduce HYbrid PRopagation (HYPR) that combines the efficiency of parallelization with approximate online forward learning. Our algorithm yields high-throughput online learning through parallelization, paired with constant, i.e., sequence length independent, memory demands. HYPR enables parallelization of parameter update computation over subsequences for RSNNs consisting of almost arbitrary non-linear spiking neuron models. We apply HYPR to networks of spiking neurons with oscillatory subthreshold dynamics. We find that this type of neuron model is particularly well trainable by HYPR, resulting in an unprecedentedly low task performance gap between approximate forward gradient learning and BPTT.

Abstract Neuromorphic computing aspires to overcome the intrinsic inefficiencies of von Neumann architectures by co-locating memory and computation in physical devices that emulate biological neurons and synapses. Memristive materials stand at the core of this paradigm, enabling non-volatile, history-dependent electronic responses. While inorganic oxides currently dominate the field, molecular and polymeric systems can offer untapped advantages in terms of chemical tunability, structural flexibility, low-cost processing, and biocompatibility. These organic memristive materials have emerged as promising building blocks for neuromorphic computing, yet their rational design is hindered by the absence of a coherent theoretical framework capable of bridging molecular-scale processes with macroscopic device behavior. Rather than proposing a new theory per se, this Perspective articulates how established multiscale theoretical and computational approaches can be systematically adapted and integrated to address the specific challenges posed by organic and molecular memristive systems. Three mechanisms-ionic migration, redox-driven switching, and conduction interplay in chiral molecules are examined as representative routes toward molecular neuromorphic hardware. By clarifying the transfer of physically meaningful parameters across computational scales and highlighting open challenges related to stability, variability, and data scarcity, this framework aims to guide future theoretical and experimental efforts in the field.

Abstract Symbol decoding in multiple-input multiple-output (MIMO) wireless communication systems requires the deployment of fast, energy-efficient computing hardware deployable at the edge. The brute-force and exact maximum likelihood (ML) decoder, solved on conventional classical digital hardware to decode MIMO symbols, has exponential time complexity. Approximate classical solvers implemented on the same hardware have polynomial time complexity at the best. In this article, we design an alternative ring-oscillator-based coupled oscillator array (also known as oscillatory neural network (ONN)) to act as an oscillator Ising machine (OIM) and heuristically solve the ML-based MIMO detection problem. Complementary metal oxide semiconductor (CMOS) technology is used to design the ring oscillators, and ferroelectric field effect transistor (FeFET) technology is chosen as the non-volatile memory (NVM) coupling element (X) between the oscillators in this CMOS + X OIM design. For this purpose, we experimentally report high linear range of conductance variation (1 µS to 60 µS) with programming voltage pulses in a HfO 2 -based FeFET device fabricated at 28 nm high-K/ metal gate (HKMG) CMOS technology node. We incorporate the conductance modulation characteristic in SPICE simulation of the ring oscillators connected in an all-to-all fashion through a crossbar array of these FeFET devices. We show that the above range of conductance variation of FeFET is suitable to obtain best OIM performance, thereby making FeFET a suitable NVM device for this application. Our SPICE simulations show that there is no significant performance drop for symbol detection up to MIMO array sizes of 90 transmitting and 90 receiving antennas. Our simulations, combined with analytical treatment using Kuramoto model of oscillators, predict that this designed classical analog OIM, if implemented experimentally, will offer logarithmic scaling of computation time with MIMO size, thereby offering huge improvement (in terms of computation speed) over exact and approximate classical solvers run on conventional digital hardware.

Abstract The majority of research in both training artificial neural networks (ANNs) and modeling learning in biological brains focuses on synaptic plasticity, where learning equates to changing the strength of existing connections. However, in biological brains, structural plasticity—where new connections are created and others removed—is also vital, not only for effective learning but also for recovery from damage and optimal resource usage. Inspired by structural plasticity, pruning is often used in machine learning (ML) to remove weak connections from trained models to reduce the computational requirements of inference. However, the ML frameworks typically used for backpropagation-based training of both ANNs and spiking neural networks (SNNs) are optimized for dense connectivity, meaning that pruning does not help reduce the training costs of ever-larger models. The GeNN simulator already supports efficient GPU-accelerated simulation of sparse SNNs for computational neuroscience and ML. Here, we present a new flexible framework for implementing GPU-accelerated structural plasticity rules and demonstrate this first using the e-prop supervised learning rule and DEEP R to train efficient, sparse SNN classifiers and then, in an unsupervised learning context, to learn topographic maps. Compared to baseline dense models, our sparse classifiers reduce training time by up to 10 × while the DEEP R rewiring enables them to perform as well as the original models. We demonstrate topographic map formation in faster-than-realtime simulations, provide insights into the connectivity evolution, and measure simulation speed versus network size. The proposed framework will enable further research into achieving and maintaining sparsity in network structure and neural communication, as well as exploring the computational benefits of sparsity in a range of neuromorphic applications.

Abstract Neuromorphic computing seeks to replicate the remarkable efficiency, flexibility, and adaptability of the human brain in artificial systems. Unlike conventional digital approaches, which suffer from the Von Neumann bottleneck and depend on massive computational and energy resources, neuromorphic systems exploit brain-inspired principles of computation to achieve orders of magnitude greater energy efficiency. By drawing on insights from a wide range of disciplines—including artificial intelligence (AI), physics, chemistry, biology, neuroscience, cognitive science and materials science—neuromorphic computing promises to deliver intelligent systems that are sustainable, transparent, and widely accessible. A central challenge, however, is to identify a unifying theoretical framework capable of bridging these diverse disciplines. We argue that stochastic dynamical systems representing equations of motion under random perturbations provide such a foundation. Rooted in differential calculus, dynamical systems theory offers a principled language for modeling inference, learning, and control in both natural and artificial substrates. Within this framework, process noise can be harnessed as a resource for learning, while differential genetic programming enables the discovery of dynamical systems that implement adaptive behaviors through stochastic adaptation across generations. Embracing this perspective paves the way toward emergent neuromorphic intelligence, where intelligent behavior arises from the dynamics of physical substrates, advancing both the science and sustainability of AI.