PROJECT TITLE :
Turn Down That Noise: Synaptic Encoding of Afferent SNR in a Single Spiking Neuron
We tend to have added a simplified neuromorphic model of Spike Time Dependent Plasticity (STDP) to the previously described Synapto-dendritic Kernel Adapting Neuron (SKAN), a hardware efficient neuron model capable of learning spatio-temporal spike patterns. The ensuing neuron model is the first to perform synaptic encoding of afferent signal-to-noise ratio additionally to the unsupervised learning of spatio-temporal spike patterns. The neuron model is significantly suitable for implementation in digital neuromorphic hardware because it will not use any advanced mathematical operations and uses a completely unique shift-primarily based normalization approach to achieve synaptic homeostasis. The neuron's noise compensation properties are characterized and tested on random spatio-temporal spike patterns along with a noise corrupted subset of the zero pictures of the MNIST handwritten digit dataset. Results show the simultaneously learning common patterns in its input information while dynamically weighing individual afferents primarily based on their signal to noise ratio. Despite its simplicity the fascinating behaviors of the neuron model and the resulting computational power could conjointly provide insights into biological systems.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here