English

Learnergy: Energy-based Machine Learners

Machine Learning 2020-09-24 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2003.07443,
  title  = {Learnergy: Energy-based Machine Learners},
  author = {Mateus Roder and Gustavo Henrique de Rosa and João Paulo Papa},
  journal= {arXiv preprint arXiv:2003.07443},
  year   = {2020}
}

Comments

12 pages, 12 figures

R2 v1 2026-06-23T14:16:44.885Z