人工智慧模型之建置與應用

10.6653/MoCICHE.201810_45(5).0008

楊明德；蔡慧萍；許鈺群；曾信鴻

土木水利

45卷5期（2018 / 10 / 01）

59 - 66

繁體中文

隨著物聯網的時代來臨，各類資料快速產生並經由網路傳遞，將巨量資料處理成有價值的資訊成為當下重要課題，人工智慧（Artificial Intelligence, AI）藉由深層類神經網路的發展與電腦計算效能提升，造就了這一波AI的浪潮。AI的組成元素可分三大項，第一為巨量資料，包括標記及未標記資料；第二是深度學習方法，包括演算法及軟硬體；第三是應用情境，包括各種AI的應用與各領域專業知識，應用的範圍涵蓋教育、服務、農業、製造、金融、醫療等人類可能觸及之各種生活情境。本文針對此三大AI組成元素進行簡要介紹，並展示一些簡單的AI模型，並提出對AI發展趨勢的觀察，希冀能迎上這波AI產業化、產業AI化的全球浪潮。

1. Apache, “MXNet: A Scalable Deep Learning Framework”, https://mxnet.apache.org/.
2. Bahdanau, D.,Kyunghyun, C.,Yoshua, B.(2014).Neural machine translation by jointly learning to align and translate.3rd International Conference on Learning Representations (ICLR2015)
3. BVLC, “Caffe | Deep Learning Framework”, http://caffe.berkeleyvi-sion.org/.
4. Cho, K.,van Merrienboer, B.,Gulcehre, C.,Bahdanau, D.,Bougares, F.,Schwenk, H.,Bengio, Y.(2014).Learning phrase representations using RNN encoder-decoder for statistical machine translation.2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (EMNLP 2014)
5. Chung, J.,Gulcehre, C.,Cho, K.,Bengio, Y.(2014).Empirical evaluation of gated recurrent neural networks on sequence modeling.NIPS 2014 Deep Learning and Representation Learning Workshop
6. Facebook., “PyTorch”, https://pytorch.org/.
7. Glorot, Xavier,Bordes, Antoine,Bengio, Yoshua(2011).Deep sparse rectifier neural networks.Proceedings of the fourteenth international conference on artificial intelligence and statistics
8. Google, “TensorFlow: An open source machine learning frameworkfor everyone”, https://www.tensorflow.org/.
9. Hochreiter, S.,Schmidhuber, J.(1997).Long short-term memory.Neural computation,9(8),1735-1780.
10. Keras-team., “Keras: Deep Learning for humans”, https://keras.io/.
11. LeCun, Y.,Bengio, Y.,Hinton, G.(2015).Deep learning.Nature,521(7553),436-444.
12. Microsoft, “The Microsoft Cognitive Toolkit”, https://www.microsoft.com/en-us/cognitive-toolkit/.
13. NVIDIA., “DIGITS: Interactive Deep Learning GPU Training System”, https://developer.nvidia.com/digits.
14. Sutskever, I.,Vinyals, O.,Le, Q.V.(2014).Sequence to sequence learning with neural networks.NIPS’14 Proceedings of the 27th International Conference on Neural Information Processing Systems

1. 陳秉訓(2023)。論人工智慧輔助之音樂創作與其著作權取得之爭議。華岡法粹，74，63-129。