论文标题
学习者：基于能量的机器学习者
Learnergy: Energy-based Machine Learners
论文作者
论文摘要
在过去的几年中，在深度学习体系结构的背景下，广泛鼓励了机器学习技术。一种令人兴奋的算法表示为受限制的玻尔兹曼机器，依赖于基于能量和概率的本质来应对最多样化的应用，例如分类，重建以及图像和信号的产生。然而，与其他众所周知的深度学习技术（例如卷积神经网络）相比，人们可以看到它们没有充分享誉。这种行为促进了文献围绕文献缺乏研究和实施，应对足够理解这些基于能量的系统的挑战。因此，在本文中，我们在基于能量的体系结构的背景下提出了一个以Python为单位的框架，称为学习者。本质上，Learnergy建立在Pytorch上，以提供更友好的环境和更快的原型工作空间，并可能使用CUDA计算，从而加快了它们的计算时间。
Throughout the last years, machine learning techniques have been broadly encouraged in the context of deep learning architectures. An exciting algorithm denoted as Restricted Boltzmann Machine relies on energy- and probabilistic-based nature to tackle the most diverse applications, such as classification, reconstruction, and generation of images and signals. Nevertheless, one can see they are not adequately renowned compared to other well-known deep learning techniques, e.g., Convolutional Neural Networks. Such behavior promotes the lack of researches and implementations around the literature, coping with the challenge of sufficiently comprehending these energy-based systems. Therefore, in this paper, we propose a Python-inspired framework in the context of energy-based architectures, denoted as Learnergy. Essentially, Learnergy is built upon PyTorch to provide a more friendly environment and a faster prototyping workspace and possibly the usage of CUDA computations, speeding up their computational time.
