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 energy-entropy relations of sensory cortical networks in the brain. Dubbed the brain-inspired cortex, the algorithm provides convergence to orthogonal features from streaming signals with superior computational efficiency while processing data in a 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 cortical coding 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.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9689639 | PMC |
http://dx.doi.org/10.3390/e24111678 | DOI Listing |
PLoS One
January 2025
Department of Biochemistry, College of Medicine, Shihezi University, Shihezi, Xinjiang, China.
Long non-coding RNAs (lncRNAs) are among the most abundant types of non-coding RNAs in the genome and exhibit particularly high expression levels in the brain, where they play crucial roles in various neurophysiological and neuropathological processes. Although ischemic stroke is a complex multifactorial disease, the involvement of brain-derived lncRNAs in its intricate regulatory networks remains inadequately understood. In this study, we established a cerebral ischemia-reperfusion injury model using middle cerebral artery occlusion (MCAO) in male Sprague-Dawley rats.
View Article and Find Full Text PDFCell Rep
January 2025
Medical Research Council Brain Network Dynamics Unit, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK. Electronic address:
Adaptive value-guided decision-making requires weighing up the costs and benefits of pursuing an available opportunity. Though neurons across frontal cortical-basal ganglia circuits have been repeatedly shown to represent decision-related parameters, it is unclear whether and how this information is coordinated. To address this question, we performed large-scale single-unit recordings simultaneously across 5 medial/orbital frontal and basal ganglia regions as rats decided whether to pursue varying reward payoffs available at different effort costs.
View Article and Find Full Text PDFiScience
January 2025
Blue Brain Project, École Polytechnique Fédérale de Lausanne (EPFL), Campus Biotech, 1202 6 Geneva, Switzerland.
We hypothesized that the heterogeneous architecture of biological neural networks provides a substrate to regulate the well-known tradeoff between robustness and efficiency, thereby allowing different subpopulations of the same network to optimize for different objectives. To distinguish between subpopulations, we developed a metric based on the mathematical theory of simplicial complexes that captures the complexity of their connectivity by contrasting its higher-order structure to a random control and confirmed its relevance in several openly available connectomes. Using a biologically detailed cortical model and an electron microscopic dataset, we showed that subpopulations with low simplicial complexity exhibit efficient activity.
View Article and Find Full Text PDFObjective: The purpose of the study was to examine the association between short-acting beta agonist (SABA), antibiotic and oral corticosteroid (OCS) use and mortality and cardiopulmonary outcomes in chronic obstructive pulmonary disease (COPD).
Design: Retrospective cohort study using administrative health data from 1 April 2011 to 31 March 2020.
Setting: Alberta, Canada.
Proc Natl Acad Sci U S A
January 2025
Modelling of Cognitive Processes, Berlin Institute of Technology, Berlin 10587, Germany.
Neuronal processing of external sensory input is shaped by internally generated top-down information. In the neocortex, top-down projections primarily target layer 1, which contains NDNF (neuron-derived neurotrophic factor)-expressing interneurons and the dendrites of pyramidal cells. Here, we investigate the hypothesis that NDNF interneurons shape cortical computations in an unconventional, layer-specific way, by exerting presynaptic inhibition on synapses in layer 1 while leaving synapses in deeper layers unaffected.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!