Learning Spike time codes through Morphological Learning with Binary Synapses
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
An algebraic approach to spike-time neural codes in the hippocampus
Although temporal coding through spike-time patterns has long been of interest in neuroscience, the specific structures that could be useful for spike-time codes remain highly unclear. Here, we introduce a new analytical…
HippocampusOpen-Ended Question AnsweringSpike-Aware C++ INT8 Inference for Sparse Spiking Language Models on Commodity CPUs
Spiking language models expose activation sparsity that dense Transformer runtimes do not directly exploit. This paper studies that property from a systems perspective. Building on the SymbolicLight V1 spike-gated langua…
Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators using Time Compression Supporting Multiple Spike Codes
Spiking neural networks (SNNs) are the third generation of neural networks and can explore both rate and temporal coding for energy-efficient event-driven computation. However, the decision accuracy of existing SNN desig…
BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning
Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two fundamental issues: the restricted information capacity of binary spi…
Representation LearningEvent-based visionLearning with precise spike times: A new decoding algorithm for liquid state machines
There is extensive evidence that biological neural networks encode information in the precise timing of the spikes generated and transmitted by neurons, which offers several advantages over rate-based codes. Here we adop…
Binary Classification