Neuromorphic computing

The Neuro Inspired Computational Elements Conference (NICE) gathers research on neuromorphic computing and its connections to neuroscience and artificial intelligence. NICE 2027 holds its main conference on 6–8 April 2027 at the University of Sussex in Brighton, United Kingdom, followed by a tutorials day of mainly hands-on two-hour tutorials on 9 April. Topics span neuromorphic hardware, analog and beyond-CMOS devices and compute-in-memory architectures; NeuroAI, including theory of neural circuits and its experimental support, local learning and plasticity, and connectomics; neuroscience-ins

INCC connects the neuromorphic computing community across neuroscience, physics, materials research and artificial intelligence. The programme combines plenary and invited presentations, contributed research talks, workshops and a characterisation laboratory supported by Advanced Microtesting. Organised by NeuroSYNC and the Aston Institute of Photonic Technologies, with NeuMat and NeuroWare as co-organisers, it brings academic and industrial researchers together to examine brain-inspired computing and build collaborations across the device-to-system ecosystem. Abstracts are due 31 October 2026

Over the past decade our community has made substantial progress in the construction of anatomically detailed network models of the cortical tissue. Thanks to advances in computer hardware and simulation technology, researchers can now routinely work with these models at the natural density of neurons and synapses. Moreover, the availability of cloud services means that such investigations can be carried out without having to install either the model or the simulation software. A recent workshop analyzed the impact of a specific model of the cortical microcircuit, published ten years ago . The

Spiking neural networks (SNNs) promise energy efficiency and offer a more brain-like alternative to artificial neural networks. However, training them on challenging tasks requiring credit assignment across long time horizons remains a significant challenge due to their discrete spiking interactions, which make the error landscape non-differentiable. A recent approach replaces the spike interactions with a surrogate gradient in the backward pass of gradient descent.\footnote{Neftci et al., \textit{Surrogate Gradient Learning in Spiking Neural Networks}, IEEE Signal Processing Magazine, 2019}\f

Spiking Neural Networks (SNNs) promise energy efficiency and offer a more brain-like alternative to artificial neural networks. A major challenge to unleashing their potential, however, is to make them trainable on challenging tasks that require credit assignment across long time horizons. Gradient-based learning, which has driven much of the recent success in ANNs, is hampered in spiking networks by their discrete spiking interactions, which make the error landscape non-differentiable. A recent approach to this challenge is to replace the spike interaction with a surrogate gradient in the bac

The brain efficiently performs nonlinear computations through its intricate networks of spiking neurons, but how this is done remains elusive. While recurrent spiking networks implementing linear computations can be directly derived and easily understood (e.g., in the spike coding network (SCN) framework), the connectivity required for nonlinear computations can be harder to interpret, as they require additional non-linearities (e.g., dendritic or synaptic) weighted through supervised training. Here we extend the SCN framework to directly implement any polynomial dynamical system. This results

For animals to navigate an uncertain world, their brains need to estimate uncertainty at the timescales of sensations and actions. Sampling-based algorithms afford a theoretically-grounded framework for probabilistic inference in neural circuits, but it remains unknown how one can implement fast sampling algorithms in biologically-plausible spiking networks. Here, we propose to leverage the population geometry, controlled by the neural code and the neural dynamics, to implement fast samplers in spiking neural networks. We first show that two classes of spiking samplers---efficient balanced spi

We introduce Norse: An open-source library for gradient-based training of spiking neural networks. In contrast to neuron simulators which mainly target computational neuroscientists, our library seamlessly integrates with the existing PyTorch ecosystem using abstractions familiar to the machine learning community. This has immediate benefits in that it provides a familiar interface, hardware accelerator support and, most importantly, the ability to use gradient-based optimization. While many parallel efforts in this direction exist, Norse emphasizes flexibility and usability in three ways. Use

…The goal of neuromorphic computing is to draw inspiration from the architecture of the brain to build low-power circuits for artificial intelligence. I will first give a brief overview of the state of the art of neuromorphic computing, highlighting the opportunities offered by emerging nanodevices in this field, and the associated challenges. I will then show that the intrinsic dynamical prope

The emergence of brain-inspired neuromorphic computing as a paradigm for edge AI is motivating the search for high-performance and efficient spiking neural networks to run on this hardware. However, compared to classical neural networks in deep learning, current spiking neural networks lack competitive performance in compelling areas. Here, for sequential and streaming tasks, we demonstrate how spiking recurrent neural networks (SRNN) using adaptive spiking neurons are able to achieve state-of-the-art performance compared to other spiking neural networks and almost reach or exceed the performa