類神經網路

臺北科技大學 115-1 學期課程，課號 364628。

課程大綱

典型神經網路之簡介與回顧、直傳式神經網路、監督式學習、非監督式學習、回傳式神經網路、神經網路之結構分析、學習方式分析神經網路之應用。 Introduction to traditional Networks, Feedback Neutral Networks ,Supervised Learning, Unsupervised Learning, Recurrant Neural Networks, Structure Analysis of Neural Networks, Analysis of Learning Methods, Applications of Neural Networks.

課程進度

Week 1_Syllabus and Overview Week 2_Introduction to Neural Network Week 3_Artificial Neural Network Architectures and Training Processes Week 4_Rosenblatt Perceptron Week 5_ADALINE Network and Delta Rule Week 6,7_Multilayer Perceptron Networks Week 8_Auxiliary Characteristics of MLP Week 9_Application of MLP Week 10_Radial Basis Function Networks Week 11_Recurrent Hopfield Networks Week 12,13_Self-Organizing Kohonen Networks Week 13,14_Learning Vector Quantization Week 15_Counter Propagation Networks Week 16_Adaptive Resonance Theory Networks Week 17,18_(Flexible Learning)Self learning on recent developments in Neural Networks

評量方式

作業與報告(Assignment and Report): 80% 期末作業(Final Assignment): 20%

教材

【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】 使用外文原文書：是 [1] Artificial Neural Networks - A Practical Course, by Da Silva et al. 2017 [2] Neural Networks and Learning Machines, by Simon Haykin. 2008 [3] Raschka, Sebastian, and Vahid Mirjalili. "Python machine learning: Machine learning and deep learning with Python, scikit-learn, and TensorFlow 2." Packt Publishing Ltd, 2019. [4] Nielsen, Michael A. "Neural networks and deep learning." Vol. 25. San Francisco, CA, USA: Determination press, 2015.