Bioinspired Cortex-based Fast Codebook Generation
This work addresses a key bottleneck in performance optimization for machine learning applications, offering potential improvements in domains such as finance, cybersecurity, and healthcare, though it appears incremental as it builds on existing clustering and feature extraction paradigms.
The paper tackles inefficient feature extraction in machine learning by introducing a bioinspired cortex algorithm that converges to orthogonal features from streaming signals with high computational efficiency. It demonstrates significantly reduced data processing time (seconds vs. hours) while maintaining similar encoding distortions compared to traditional clustering methods like Birch, GMM, and K-means.
A major archetype of artificial intelligence is developing algorithms facilitating temporal efficiency and accuracy while boosting the generalization performance. Even with the latest developments in machine learning, a key limitation has been the inefficient feature extraction from the initial data, which is essential in performance optimization. Here, we introduce a feature extraction method inspired by sensory cortical networks in the brain. Dubbed as bioinspired cortex, the algorithm provides convergence to orthogonal features from streaming signals with superior computational efficiency while processing data in compressed form. We demonstrate the performance of the new algorithm using artificially created complex data by comparing it with the commonly used traditional clustering algorithms, such as Birch, GMM, and K-means. While the data processing time is significantly reduced, seconds versus hours, encoding distortions remain essentially the same in the new algorithm providing a basis for better generalization. Although we show herein the superior performance of the cortex model in clustering and vector quantization, it also provides potent implementation opportunities for machine learning fundamental components, such as reasoning, anomaly detection and classification in large scope applications, e.g., finance, cybersecurity, and healthcare.