The field of neuromorphic computing and spiking neural networks is rapidly advancing, with a focus on developing more efficient and adaptive computing systems inspired by the human brain. Recent research has explored the use of spiking neural networks (SNNs) for energy-efficient computation, with applications in areas such as robotics, neuromorphic vision, and edge AI systems. SNNs have been shown to be particularly well-suited for spatio-temporal tasks, such as keyword spotting and video classification, and have achieved state-of-the-art performance in certain benchmarks. Additionally, researchers have been investigating the use of novel hardware platforms, such as memristor-based systems, to support the development of more efficient and scalable neuromorphic computing systems. Noteworthy papers in this area include the development of a high-throughput SNN processor, the introduction of a novel neuron position learning algorithm, and the creation of an open-source memristor interfacing and compute board for neuromorphic edge-AI applications. These advances have the potential to enable the development of more efficient and adaptive computing systems, with applications in a wide range of fields.
Advances in Neuromorphic Computing and Spiking Neural Networks
Sources
Ferrohydrodynamic Microfluidics for Bioparticle Separation and Single-Cell Phenotyping: Principles, Applications, and Emerging Directions
Practical Timing Closure in FPGA and ASIC Designs: Methods, Challenges, and Case Studies
Lorentzian Switching Dynamics in HZO-based FeMEMS Synapses for Neuromorphic Weight Storage
Spiking Neural Networks: The Future of Brain-Inspired Computing
Exploiting heterogeneous delays for efficient computation in low-bit neural networks
ReLaX-Net: Reusing Layers for Parameter-Efficient Physical Neural Networks
High-Power Dual-Channel Field Chamber for High-Frequency Magnetic Neuromodulation
FeNN-DMA: A RISC-V SoC for SNN acceleration
Random Spiking Neural Networks are Stable and Spectrally Simple
Neuro-Inspired Task Offloading in Edge-IoT Networks Using Spiking Neural Networks
A High-Throughput Spiking Neural Network Processor Enabling Synaptic Delay Emulation
Real-time Continual Learning on Intel Loihi 2
Space as Time Through Neuron Position Learning
Facial Expression Recognition System Using DNN Accelerator with Multi-threading on FPGA
Reliability entails input-selective contraction and regulation in excitable networks
Redundancy Maximization as a Principle of Associative Memory Learning
OpenMENA: An Open-Source Memristor Interfacing and Compute Board for Neuromorphic Edge-AI Applications
Neural Computation Without Slots: Steps Towards Biologically Plausible Memory and Attention in Natural and Artificial Intelligence