There are great challenges to build a model or architecture in Deep Learning and integrate it into a real-time application. One of these challenges is the construction or acquisition of large quality datasets (thousands or millions of objects). Another one is to have great computing potential for the architecture learning process. Finally, efficient architectures are needed for the design of deep neural networks, which requires expertise, human experience and practical work. This work presents a deep neural network architecture to classify two feelings of facial expression (happy and sad). A set of data is also created that present great changes in: image environments, facial expression, pose, age, ethnicity and others. The evidence presented shows a competitive architecture and indicates an accuracy greater than 90% with noisy data. Finally, the implementation of a real-time application for facial expression recognition is shown.

中文翻译：

---

深度神经网络架构：面部表情识别的应用

在深度学习中构建模型或架构并将其集成到实时应用程序中存在巨大挑战。这些挑战之一是构建或获取大型质量数据集（数千或数百万个对象）。另一个是在架构学习过程中具有巨大的计算潜力。最后，深度神经网络的设计需要高效的架构，这需要专业知识、人类经验和实际工作。这项工作提出了一种深度神经网络架构来对两种面部表情（快乐和悲伤）进行分类。还创建了一组数据，这些数据在以下方面发生了巨大变化：图像环境、面部表情、姿势、年龄、种族等。所提供的证据显示了一个有竞争力的架构，并表明在噪声数据下的准确度超过 90%。最后，