卷積神經網路 Convolutional Neural Networks · 資料科學・機器・人

每當深度學習又有什麼重大突破時，這些進展十有八九都和卷積神經網路（Convolutional Neural Networks，CNN）有關。CNN 又被稱為 CNNs 或 ConvNets，它是目前深度神經網路（deep neural network）領域的發展主力，在圖片辨別上甚至可以做到比人類還精準的程度。如果要說有任何方法能不負大家對深度學習的期望，CNN 絕對是首選。

卷積神經網路 Convolutional Neural Networks · 資料科學・機器・人 Powered by GitBook 卷積神經網路 Convolutional Neural Networks 卷積神經網路的運作原理 原文： How do Convolutional Neural Networks work? Translated from Brandon Rohrer's Blog by Jimmy Lin 相關連結： PDF（2MB） 、 PPT（6MB） 日文版 波&#x65A

related reading

• Convolutional Neural Networks, Explained | Towards Data Sciencetowardsdatascience.com
• CS231n Deep Learning for Computer Visioncs231n.github.io
• A Beginner's Guide To Understanding Convolutional Neural Networks – Adit Deshpande – Engineering at Forward | UCLA CS '19adeshpande3.github.io
• 遞歸神經網路和長短期記憶模型 RNN & LSTM · 資料科學・機器・人brohrer.mcknote.com
• Zoom In: An Introduction to Circuitsdistill.pub
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Neural Networks, Types, and Functional Programming -- colah's blogcolah.github.io
• The Decade of Deep Learning | Leo Gaobmk.sh
• Convolutional Neural Network (CNN) | TensorFlow Coretensorflow.org
• Convolution Vs Correlation | Towards Data Sciencetowardsdatascience.com
• Dense CNNsarxiv.org
• [1811.12231] ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessarxiv.org