Memory via Temporal Delays in weightless Spiking Neural Network
This work addresses memory encoding for neuroscience and AI by introducing a novel paradigm, though it is a prototype with limited scope.
The paper tackled the problem of memory encoding in neural networks by proposing a weightless spiking neural network prototype that stores memory in temporal delays between neurons instead of connection strengths, achieving performance on a simple classification task using Hebbian STDP training.
A common view in the neuroscience community is that memory is encoded in the connection strength between neurons. This perception led artificial neural network models to focus on connection weights as the key variables to modulate learning. In this paper, we present a prototype for weightless spiking neural networks that can perform a simple classification task. The memory in this network is stored in the timing between neurons, rather than the strength of the connection, and is trained using a Hebbian Spike Timing Dependent Plasticity (STDP), which modulates the delays of the connection.