The spectacular results achieved in machine learning, including the recent advances in generative AI, rely on large data collections. On the opposite, intelligent processes in nature arises without the need for such collections, but simply by online processing of the environmental information. In particular, natural learning processes rely on mechanisms where data representation and learning are intertwined in such a way to respect spatiotemporal locality. This paper shows that such a feature arises from a pre-algorithmic view of learning that is inspired by related studies in Theoretical Physics. We show that the algorithmic interpretation of the derived "laws of learning", which takes the structure of Hamiltonian equations, reduces to Backpropagation when the speed of propagation goes to infinity. This opens the doors to machine learning studies based on full on-line information processing that are based the replacement of Backpropagation with the proposed spatiotemporal local algorithm.
Exhaustive Exploitation of Nature-inspired Computation for Cancer Screening in an Ensemble Manner
School of Artificial Intelligence, Jilin University(吉林大学人工智能学院);School of Artificial Intelligence, Hebei University of Technology(河北工业大学人工智能学院);School of Information Science and Technology, Northeast Normal University(东北师范大学信息科学与技术学院);Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系)
Applications of Nature-Inspired Algorithms for Dimension Reduction: Enabling Efficient Data Analytics
University of Georgia(佐治亚大学);Franklin College of Arts and Sciences(富兰克林文理学院);Florida International University(佛罗里达国际大学);College of Engineering and Computing(工程与计算学院)
在[1]中,我们已经探索了特征选择和进化算法的理论方面。在本章中,我们重点介绍用于增强数据分析过程的优化算法,即,我们建议探索自然启发算法在数据科学中的应用。特征选择优化是一种利用特征选择技术和进化算法过程来优化所选特征的混合方法。以前的作品迭代地解决这个问题,收敛到一个最佳的特征子集。特征选择优化是一种非特定领域的方法。数据科学家主要试图找到一种先进的方法来分析数据,具有高计算效率和低时间复杂度,从而导致有效的数据分析。因此,通过增加来自各种来源的生成/测量/感测的数据,数据的分析、操纵和说明呈指数增长。由于数据集规模庞大,维数灾难(Curse of Dimensionality,CoD)是数据科学中的NP难题之一。因此,一些努力已经集中在利用进化算法(EA)来解决大规模数据分析问题中的复杂问题。降维与EA一起,有助于解决CoD和解决复杂问题,在时间复杂度方面,有效地。在这一章中,我们首先提供了一个简短的概述,以前的研究,重点是解决CoD使用特征提取优化过程。然后,我们讨论了研究的实际例子,成功地解决了一些应用领域,如图像处理,情感分析,网络流量/异常分析,信用评分分析和其他基准功能/数据集分析。
Biology-inspired joint distribution neurons based on Hierarchical Correlation Reconstruction allowing for multidirectional propagation of values and densities
StochEP: Stochastic Equilibrium Propagation for Spiking Convergent Recurrent Neural Networks
School of Electrical Engineering and Computer Science(电气工程与计算机科学学院);The Pennsylvania State University(宾夕法尼亚州立大学);University Park(大学公园);PA 16802, USA(宾夕法尼亚州16802, 美国)