DLOPT: Deep Learning Optimization Library

2018/07/10 by Andrés Camero, Camero, Andrés, Jamal Toutouh +3
Computer Science · Engineering · Mathematics · #Advanced Neural Network Applications #Anomaly Detection Techniques and Applications #Architecture #Artificial intelligence #Computer science #Deep learning #Engineering #FOS: Computer and information sciences #Key (lock) #License #MIT License #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Neural and Evolutionary Computing (cs.NE) #Open source #Operating system #Programming language #Set (abstract data type) #Software #Task (project management) #cs.LG #cs.NE #stat.ML

paper · pdf · doi:10.48550/arxiv.1807.03523

4 pages

arxiv created 2018/07/10 · openalex publication_date 2018/07/10 · arxiv updated 2018/07/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep learning hyper-parameter optimization is a tough task. Finding an appropriate network configuration is a key to success, however most of the times this labor is roughly done. In this work we introduce a novel library to tackle this problem, the Deep Learning Optimization Library: DLOPT. We briefly describe its architecture and present a set of use examples. This is an open source project developed under the GNU GPL v3 license and it is freely available at https://github.com/acamero/dlopt

Citations

• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Low-Cost Recurrent Neural Network Expected Performance Evaluation

Related

• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• DeepOBS: A Deep Learning Optimizer Benchmark Suite
• DEEP-BO for Hyperparameter Optimization of Deep Networks
• A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities
• A Data-Centric Optimization Framework for Machine Learning