工程與環境統計領域選修課程之一。

機器學習是近年發展最快速的AI議題之一，其中以類神經網路(ANNs)為主的深度學習技術結合巨量資料的處理與應用漸趨熱切，如何快速有效地從資料中篩選、萃取、分類及解析出有用的資訊，創造出高價值的服務，實為一大挑戰。類神經網路具有從環境中擷取資訊，自我學習，從而做出推論之能力，利用電腦的軟體來模擬生物神經系統的資訊處理方式，由人類專家解決問題的實際案例中學習，利用統計、分類、非線性函數的轉換及最佳化原理等，能有效地對大量且複雜之資訊進行統計分析、分類、判識、推估等。類神經網路可解決過去傳統的電腦資訊理論中一些難以突破的瓶頸，例如：生物醫農領域中之判識、分類或推論；工程、科學與資訊管理領域中之模擬與預測、最佳化管理、非線性系統識別、圖形和語音的辨識、自動控制駕駛、電腦遊戲、或者是處理邏輯上的問題等。本課程藉由深入淺出說明ANNs的相關理論與展示實際研究案例，很適合對ANNs基本原理具濃厚興趣 及/或 想運用類神經網路科技解決地球科學、生態環境、生物醫學、工程與工商管理領域相關問題之同學共同來研習。

Artificial Neural networks is one of the main constitutional intelligence, the set of biological inspired computing paradigms used to learn and establish baseline behavioral profiles for various entities based on big data. ANNs can play an important role in solving certain problems in science and engineering such as forecasting, pattern recognition, optimization and identification of nonlinear systems etc. This course will cover the basic components of building and applying prediction functions with an emphasis on practical applications. The course will provide basic grounding in concepts such as training and tests sets, overfitting, and error rates. The course will also introduce a range of machine learning algorithms including BPNN, RBFNN, SOM, RNN, CFNN, ANFIS as well as deep learning algorithms such as LSTM and CNN. The course is primarily intended for those individuals, who want to understand the underlying principles of artificial neural networks and want to be able to apply various neurocomputing techniques to solve problems in earth sciences, business administration, ecological environment, biomedical, and engineering.

待補

Textbook: 張斐章、張麗秋，「類神經網路導論：原理與應用(第二版)(CD Inside)」，滄海書局，2015 年。 References: 1. Simon Haykin; Neural Networks – A comprehensive foundation, 3nd Edition, 2009. 2. 類神經網路相關期刊論文導讀 ( https://www.researchgate.net/profile/Fi- John_Chang/stats )