首页|New Findings from Indian Institute of Science in Machine Learning Provides New I nsights (Development of a Novel Transformation of Spiking Neural Classifier To a n Interpretable Classifier)
New Findings from Indian Institute of Science in Machine Learning Provides New I nsights (Development of a Novel Transformation of Spiking Neural Classifier To a n Interpretable Classifier)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Machine Learning. According to news originating from Bengaluru, India, by NewsRx correspondents, research stated, "This article presents a new approach for prov iding an interpretation for a spiking neural network classifier by transforming it to a multiclass additive model. The spiking classifier is a multiclass synapt ic efficacy function-based leaky-integrate-fire neuron (Mc-SEFRON) classifier." Financial supporters for this research include Agency for Science Technology & Research (A*STAR), National Research Foundation, Singapore, under its AI Singapo re Programme (AISG). Our news journalists obtained a quote from the research from the Indian Institut e of Science, "As a first step, the SEFRON classifier for binary classification is extended to handle multiclass classification problems. Next, a new method is presented to transform the temporally distributed weights in a fully trained Mc-SEFRON classifier to shape functions in the feature space. A composite of these shape functions results in an interpretable classifier, namely, a directly inter pretable multiclass additive model (DIMA). The interpretations of DIMA are also demonstrated using the multiclass Iris dataset. Further, the performances of bot h the Mc-SEFRON and DIMA classifiers are evaluated on ten benchmark datasets fro m the UCI machine learning repository and compared with the other state-of-the-a rt spiking neural classifiers. The performance study results show that Mc-SEFRON produces similar or better performances than other spiking neural classifiers w ith an added benefit of interpretability through DIMA. Furthermore, the minor di fferences in accuracies between Mc-SEFRON and DIMA indicate the reliability of t he DIMA classifier. Finally, the Mc-SEFRON and DIMA are tested on three real-wor ld credit scoring problems, and their performances are compared with state-of-th e-art results using machine learning methods."
BengaluruIndiaAsiaCyborgsEmergin g TechnologiesMachine LearningIndian Institute of Science
NETL
NSTL
