基於多模態主動式學習法進行需備標記樣本之挑選用於候用校長評鑑之自動化評分系統建置

A Multimodal Active Learning Approach toward Identifying Samples to Label during the Development of Automatic Oral Presentation Assessment System for Pre-service Principals Certification Program

主動式學習（active learning）在機器學習領域中越來越受到重視，因為它可以用來優化訓練的過程，讓結果更好。主要的概念是假如學習演算法可以在學習的過程中選擇比較決定性的資料點而不是挑選全部資料來做學習。接著根據對於模型而言具有代表性的資料點做挑選，將會對於學習的效果更有幫助，獲得更佳的結果。換句話說，透過觀察已知的標記資料，主動地挑選未標記的資料，並藉此獲得比挑選全部資料或是隨機抽樣資料的監督式學習方式更高的準確率以及更少的資料量。對於任何監督式學習（supervised learning）來說，假如想要促使學習系統表現的更好，則需要大量的被標記的資料來做訓練。但是，在這些被標記的資料中，可能會存在著對於學習系統有著負面影響的資料，從而降低學習效果與準確率。在這篇論文中，我們將會應用主動式學習的概念在系統學習的過程上，藉此來分辨資料對於系統的好壞；並測試主動式學習在訓練過程中的實際效果。

Active learning is becoming more and more important in machine learning that can optimize the learning process. The main concept is that if learning algorithm can choose the most informative data points from which it learns, instead of choosing all of them, it will perform better with less training. In other words, we recursively select the unlabeled data instances by observing the known labeled data instances to obtain higher recognition accuracy while using smaller amounts of data instances, i.e., a subset of all of the dataset or random choose data when training the supervised learning system. For any supervised learning, if you would like to make the system perform well, it had to be trained on lots of labeled instances. But, in these labeled instances, there might be some worthless instances which affect the learning system and raise your training cost. So, we used the active learning concept during training process to discriminate whether the data instance is good for the learning system or not. In this work, we would like to know that the concept of active learning to select the training data, will work or not.