Custom DNN using Reward Modulated Inverted STDP Learning for Temporal Pattern Recognition
This work addresses efficient pattern recognition in sparse event series for applications like anomaly detection and keyword spotting, representing an incremental improvement.
The paper tackles temporal spike pattern recognition by proposing a novel algorithm that combines reward-modulated learning with Hebbian and anti-Hebbian methods, achieving performance comparable to state-of-the-art on a spoken digits dataset.
Temporal spike recognition plays a crucial role in various domains, including anomaly detection, keyword spotting and neuroscience. This paper presents a novel algorithm for efficient temporal spike pattern recognition on sparse event series data. The algorithm leverages a combination of reward-modulatory behavior, Hebbian and anti-Hebbian based learning methods to identify patterns in dynamic datasets with short intervals of training. The algorithm begins with a preprocessing step, where the input data is rationalized and translated to a feature-rich yet sparse spike time series data. Next, a linear feed forward spiking neural network processes this data to identify a trained pattern. Finally, the next layer performs a weighted check to ensure the correct pattern has been detected.To evaluate the performance of the proposed algorithm, it was trained on a complex dataset containing spoken digits with spike information and its output compared to state-of-the-art.