New AI Mimics Brain to Work Faster on Your Phone
This could make your phone's AI faster and more battery-friendly.
Exploiting temporal information in datasets with high temporal dependencies (such as spoken keyword recognition) by spiking models is still an open problem. Promising frameworks include Time-To-First coding (TTFS) and the inclusion of synaptic delays into learning. In TTFS, neurons are forced to spike at most once, forcing the network to found its learning on the spiking times of neurons rather than their spiking rate.
Some models use the TTFS framework to directly compute the spiking time of Integrate-and-Fire (IF) or Leaky Integrate-and-Fire (LIF) neurons. However, most models built in the TTFS framework have not been tested against datasets containing temporal information. Little is known about the latency of these models on temporal datasets, where the latency is the time taken by the network to correctly classify a sample.
In this work, we study the behaviour of Delay Neural Networks (DeNN) models, i.e. models that directly compute the spiking time of neurons by bypassing the membrane potential and thresholding mechanisms of spiking neurons. We show how to analytically control their latency, and empirically study the latency-accuracy tradeoff in a dynamic temporal dataset.
- Spiking neural networks are AI that mimic the brain's spikes, but they often have delays.
- New method controls timing to make them faster, which could lead to quicker AI on devices.
- This could mean longer battery life and real-time responses in future gadgets.
Why It Matters
Faster, more efficient AI could make your devices smarter and battery last longer.