SNNS
PulseAugur coverage of SNNS — every cluster mentioning SNNS across labs, papers, and developer communities, ranked by signal.
-
New memristive synapse enables online learning in spiking neural networks
Researchers have developed an analog memristive synaptic circuit designed for online learning in spiking neural networks (SNNs). This circuit enables gradual conductance updates directly from pre- and post-synaptic spik…
-
New analog readout architecture enhances SNN efficiency
Researchers have developed a novel analog readout architecture for spiking neural networks (SNNs) that utilizes voltage-to-time conversion. This approach aims to improve area and energy efficiency by eliminating the nee…
-
New MeMark technique embeds watermarks in SNN neuron states
Researchers have developed a new watermarking technique called MeMark for Spiking Neural Networks (SNNs) to protect against unauthorized reuse of pre-trained models. Unlike previous methods that focused on output verifi…
-
New "sponge attacks" exploit SNN energy efficiency for increased power consumption
Researchers have identified a new security vulnerability in Spiking Neural Networks (SNNs) that exploits their energy efficiency. Dubbed "sponge attacks," these methods can significantly increase the energy consumption …
-
Spiking Neural Networks' energy efficiency tied to task, not architecture
A new research paper explores the energy efficiency of Spiking Neural Networks (SNNs), arguing that the benefits of sparsity are task-dependent rather than inherent to SNNs. The study found that while feed-forward perce…
-
AI models use 'relocation' in latent space for covert communication
Researchers have explored how AI models can communicate covertly by relocating signals within their latent space, rather than obfuscating them. In experiments using SpikeGPT, a spiking neural network based on the RWKV a…
-
Hybrid SNN-CNN models enhance fall detection with efficient event data processing
Researchers have developed hybrid models combining spiking neural networks (SNNs) with convolutional neural networks (CNNs) to improve fall detection. These models process simulated event-based camera data, generated fr…
-
QB-LIF neuron boosts SNN efficiency with learnable scale and burst spiking
Researchers have introduced QB-LIF, a novel neuron model for spiking neural networks (SNNs) that addresses the information throughput limitations of binary spike coding. QB-LIF reformulates burst spiking using a learnab…