Spike-timing dependent plasticity
PulseAugur coverage of Spike-timing dependent plasticity — every cluster mentioning Spike-timing dependent plasticity across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Spiking Neural Networks improved for visual place recognition · 2 sources tracked
Researchers have developed a new implementation of Spiking Neural Networks (SNNs) using PyTorch and snnTorch for visual place recognition. This discrete, tensor-native approach aims to improve Recall at 100% Precision (…
-
New research shows local synaptic rules can enable self-supervised learning without backpropagation
Researchers have demonstrated that local synaptic learning rules, specifically spike-timing-dependent plasticity (STDP+) and homeostatic plasticity, can effectively implement a SIGReg gradient for self-supervised learni…
-
Neuromorphic Silicon Suite Unveiled for Edge AI Systems
Researchers have developed a suite of four digital intellectual property (IP) blocks for edge neuromorphic systems, implemented in standard-cell CMOS on the SkyWater 130 nm process. These blocks include a process, volta…
-
New ITP-STDP engine slashes SNN training energy use
Researchers have developed a new learning engine called ITP-STDP for training spiking neural networks (SNNs) that significantly reduces hardware resource utilization and energy consumption. This novel approach optimizes…
-
Backpropagation degrades neural network brain alignment within one epoch
A new research paper reveals that standard supervised training methods, particularly backpropagation, can rapidly degrade the alignment of artificial neural networks with the early visual cortex of the human brain. This…
-
AI learning rules align with early primate vision, diverge in higher areas
Researchers have published a study comparing how different learning rules in artificial neural networks align with visual processing in both humans and macaques. The study found that early visual cortex alignment was co…
-
Spiking neural networks propose temporal coding for object recognition
Researchers have proposed a new method for object recognition that utilizes temporal coding in spiking neural networks, offering a reinterpretation of the Thousand Brains Architecture. This approach replaces dense vecto…
-
Untrained CNNs match human visual cortex at V1, research finds
A new study published on arXiv investigates how different learning rules in neural networks compare to human brain activity in visual processing. Researchers found that for early visual areas like V1 and V2, the network…