论文标题
绘制您的神经网络
Draw your Neural Networks
论文作者
论文摘要
深度神经网络是现代人工智能的基本基础。由于它们能够直接从数据中学习以及各种任务的精确度，因此他们越来越多地替换或增强现有软件系统。现有的软件开发生命周期（SDLC）方法论在代表AI开发的独特功能和要求方面缺乏，必须用人工智能开发生命周期（AIDLC）方法代替。在本文中，我们讨论了一种替代性，更自然的方法来开发涉及直观的GUI元素（例如块和线路）来绘制它们而不是复杂的计算机编程的神经网络。我们提出了草图框架，该框架使用这种基于GUI的方法来设计和修改神经网络，并提供与传统框架的互操作性。该系统提供流行的层次和操作，并可以导入任何受支持的预培训模型，从而使其成为设计和训练复杂的神经网络并最终通过删除学习曲线使AI民主化的方法。
Deep Neural Networks are the basic building blocks of modern Artificial Intelligence. They are increasingly replacing or augmenting existing software systems due to their ability to learn directly from the data and superior accuracy on variety of tasks. Existing Software Development Life Cycle (SDLC) methodologies fall short on representing the unique capabilities and requirements of AI Development and must be replaced with Artificial Intelligence Development Life Cycle (AIDLC) methodologies. In this paper, we discuss an alternative and more natural approach to develop neural networks that involves intuitive GUI elements such as blocks and lines to draw them instead of complex computer programming. We present Sketch framework, that uses this GUI-based approach to design and modify the neural networks and provides interoperability with traditional frameworks. The system provides popular layers and operations out-of-the-box and could import any supported pre-trained model making it a faster method to design and train complex neural networks and ultimately democratizing the AI by removing the learning curve.
