Deep neural network (DNN) and its variants have been extensively used for a wide spectrum of real applications such as image classification, face/speech recognition, fraud detection, and so on. In addition to many important machine learning tasks, as artificial networks emulating the way brain cells function, DNNs also show the capability of storing non-linear relationships between input and output data, which exhibits the potential of storing data via DNNs. We envision a new paradigm of data storage, "DNN-as-a-Database", where data are encoded in well-trained machine learning models. Compared with conventional data storage that directly records data in raw formats, learning-based structures (e.g., DNN) can implicitly encode data pairs of inputs and outputs and compute/materialize actual output data of different resolutions only if input data are provided. This new paradigm can greatly enhance the data security by allowing flexible data privacy settings on different levels, achieve low space consumption and fast computation with the acceleration of new hardware (e.g., Diffractive Neural Network and AI chips), and can be generalized to distributed DNN-based storage/computing. In this paper, we propose this novel concept of learning-based data storage, which utilizes a learning structure called learning-based memory unit (LMU), to store, organize, and retrieve data. As a case study, we use DNNs as the engine in the LMU, and study the data capacity and accuracy of the DNN-based data storage. Our preliminary experimental results show the feasibility of the learning-based data storage by achieving high (100%) accuracy of the DNN storage. We explore and design effective solutions to utilize the DNN-based data storage to manage and query relational tables. We discuss how to generalize our solutions to other data types (e.g., graphs) and environments such as distributed DNN storage/computing.
翻译:深神经网络(DNN) 及其变体被广泛用于一系列广泛的真实应用, 如图像分类、脸孔/声音识别、欺诈检测等。除了许多重要的机器学习任务, 模拟脑细胞功能的人工网络, DNN 也显示在输入和输出数据之间储存非线性关系的能力, 这显示出通过 DNN 存储数据的潜力。 我们设想了一个新的数据存储模式, “ DNN-as- a-Database ”, 数据在经过良好训练的机器学习模型中编码。 与直接记录原始格式数据的准确性的传统数据存储模式相比, 学习基础结构( 例如, DNNNN) 可以隐含地编码输入和产出的数据组合, 并且仅仅提供输入输入数据数据数据数据数据, 新的模式可以大大提高数据安全性, 允许在不同级别上灵活的数据隐私设置, 实现低空间消耗和快速计算, 加速新硬件( 例如, Diffral Net 网络 和 AI Chick ) 数据存储, 和 数据库 数据库 数据库数据库数据库数据库数据库数据库数据库数据库数据库 数据库数据库数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库 数据库