Related papers: ETLP: Event-based Three-factor Local Plasticity fo…
As deep learning models scale, they become increasingly competitive from domains spanning from computer vision to natural language processing; however, this happens at the expense of efficiency since they require increasingly more memory…
Although widely used in machine learning, backpropagation cannot directly be applied to SNN training and is not feasible on a neuromorphic processor that emulates biological neuron and synapses. This work presents a spike-based…
On-chip learning is key to scalable and adaptive neuromorphic systems, yet existing training methods are either difficult to implement in hardware or overly restrictive. However, recent studies show that feedback-control optimizers can…
As large language models continue to scale in size rapidly, so too does the computational power required to run them. Event-based networks on neuromorphic devices offer a potential way to reduce energy consumption for inference…
Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory, especially in continual learning. We propose Local…
Reliable visual place recognition (VPR) under dynamic real-world conditions is critical for autonomous robots, yet conventional deep networks remain limited by high computational and energy demands. Inspired by the mammalian navigation…
Magnetic skyrmions, as scalable and non-volatile spin textures, can dynamically interact with fields and currents, making them promising for unconventional computing. This paper presents a neuromorphic device based on skyrmion manipulation…
Brain-inspired neuromorphic technologies can offer important advantages over classical digital clock-based technologies in various domains, including systems and control engineering. Indeed, neuromorphic engineering could provide…
We introduce Spike Agreement Dependent Plasticity (SADP), a biologically inspired synaptic learning rule for Spiking Neural Networks (SNNs) that relies on the agreement between pre- and post-synaptic spike trains rather than precise…
In this paper, we propose a design methodology to partition and map the neurons and synapses of online learning SNN-based applications to neuromorphic architectures at {run-time}. Our design methodology operates in two steps -- step 1 is a…
The rising demand for energy-efficient edge AI systems (e.g., mobile agents/robots) has increased the interest in neuromorphic computing, since it offers ultra-low power/energy AI computation through spiking neural network (SNN) algorithms…
Configurable synaptic delays are a basic feature in many neuromorphic neural network hardware accelerators. However, they have been rarely used in model implementations, despite their promising impact on performance and efficiency in tasks…
Understanding how recurrent neural circuits can learn to implement dynamical systems is a fundamental challenge in neuroscience. The credit assignment problem, i.e. determining the local contribution of each synapse to the network's global…
The increasing need for compact and low-power computing solutions for machine learning applications has triggered significant interest in energy-efficient neuromorphic systems. However, most of these architectures rely on spiking neural…
Neuromorphic computing-modelled after the functionality and efficiency of biological neural systems-offers promising new directions for advancing artificial intelligence and computational models. Photonic techniques for neuromorphic…
Event-based machine learning promises more energy-efficient AI on future neuromorphic hardware. Here, we investigate how the recently discovered Eventprop algorithm for gradient descent on exact gradients in spiking neural networks can be…
Edge computing scenarios necessitate the development of hardware-efficient online continual learning algorithms to be adaptive to dynamic environment. However, existing algorithms always suffer from high memory overhead and bias towards…
We propose a scalable neuromorphic architecture based on spiking dynamics emerging from the autonomous time-continuous evolution of clockless (asynchronous) digital circuits. Implemented on commercially available field-programmable gate…
Spike-Timing Dependent Plasticity (STDP) is believed to play an important role in learning and the formation of computational function in the brain. The classical model of STDP which considers the timing between pairs of pre-synaptic and…
The deployment of Artificial Intelligence on edge devices (TinyML) is often constrained by the high power consumption and latency associated with traditional Artificial Neural Networks (ANNs) and their reliance on intensive Matrix-Multiply…