Spiking Neuromorphic Transformer Achieves Attention Via Synaptic Plasticity, Reducing Energy Costs Beyond 0.49

Emerging Synaptic Memory Technologies For Neuromorphic CIM Platforms (Tampere Univ.)

A new technical paper titled “Toward Capacitive In-Memory-Computing: A Device to Systems Level Perspective on the Future of Artificial Intelligence Hardware” was published by researchers at Tampere University. Abstract: “The quest for energy-efficient, scalable neuromorphic computing has elevated compute-in-memory (CIM) architectures to the forefront of hardware innovation. While memristive memories, such as resistive random-access memories, pha…

Spiking Neuromorphic Transformer Achieves Attention Via Synaptic Plasticity, Reducing Energy Costs Beyond 0.49

Researchers have created a new artificial intelligence model that mimics the brain’s attention mechanism using spike-timing-dependent plasticity, achieving high accuracy on image recognition tasks with significantly reduced energy consumption and paving the way for more sustainable AI hardware.