Apparatus for classifying sounds based on neural code in spiking neural network and method thereof

A method of classifying sounds using an apparatus for classifying sounds based on a neural code in a spiking neural network, the method comprising:

• receiving sounds to be classified and digitally converting the received sounds into sound data;
• preprocessing the sound data using a multiple neural code-based encoding method including both rate code encoding to represent pitch and synchrony code encoding to represent sound intensity and timbre;
• inputting the rate code-encoded sound data and the synchrony code-encoded sound data into a biological spiking neural network configured to process each type of neural code along separate propagation pathways;
• extracting features from neuron activity corresponding to distinct propagation patterns of the rate and synchrony codes;
• performing biological spike timing-dependent plasticity (STDP) rule-based learning using the extracted features, wherein STDP rules are applied differently to respective propagation patterns of the rate code and the synchrony code;
• and
• classifying the sounds based on differences in neural code propagation characteristics using a test dataset derived from a result of the STDP rule-based learning.