Learning Spike time codes through Morphological Learning with Binary Synapses
This work addresses the challenge of efficient and robust spike-time coding for hardware applications, such as tactile sensing, but it is incremental as it builds on existing temporal learning algorithms.
The paper tackles the problem of learning temporal spike patterns with binary synapses by introducing a neuron with nonlinear dendrites and a morphological learning algorithm that adapts thresholds during training. It achieves similar accuracy to a traditional method with higher-bit synapses in classifying spike patterns, making it more suitable for robust hardware implementation.
In this paper, a neuron with nonlinear dendrites (NNLD) and binary synapses that is able to learn temporal features of spike input patterns is considered. Since binary synapses are considered, learning happens through formation and elimination of connections between the inputs and the dendritic branches to modify the structure or "morphology" of the NNLD. A morphological learning algorithm inspired by the 'Tempotron', i.e., a recently proposed temporal learning algorithm-is presented in this work. Unlike 'Tempotron', the proposed learning rule uses a technique to automatically adapt the NNLD threshold during training. Experimental results indicate that our NNLD with 1-bit synapses can obtain similar accuracy as a traditional Tempotron with 4-bit synapses in classifying single spike random latency and pair-wise synchrony patterns. Hence, the proposed method is better suited for robust hardware implementation in the presence of statistical variations. We also present results of applying this rule to real life spike classification problems from the field of tactile sensing.