Injective Domain Knowledge in Neural Networks for Transprecision Computing
| Autor: | Michele Lombardi, Federico Baldo, Michela Milano, Andrea Borghesi |
|---|---|
| Přispěvatelé: | Giuseppe Nicosia, Varun Kumar Ojha, Emanuele La Malfa, Giorgio Jansen, Vincenzo Sciacca, Panos M. Pardalos, Giovanni Giuffrida, Renato Umeton, Andrea Borghesi, Federico Baldo, Michele Lombardi, Michela Milano |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Scarce data Computer Science - Machine Learning Theoretical computer science Artificial neural network Computer science Computer Science - Artificial Intelligence Machine Learning (stat.ML) 02 engineering and technology Injective function Machine Learning (cs.LG) 020202 computer hardware & architecture Machine Learning Constraints Domain Knowledge Artificial Intelligence (cs.AI) Pure Data Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Domain knowledge 020201 artificial intelligence & image processing computer computer.programming_language |
| Zdroj: | Machine Learning, Optimization, and Data Science ISBN: 9783030645823 LOD (1) Machine Learning, Optimization, and Data Science-6th International Conference, LOD 2020, Siena, Italy, July 19–23, 2020, Revised Selected Papers, Part I Lecture Notes in Computer Science Lecture Notes in Computer Science-Machine Learning, Optimization, and Data Science |
| ISSN: | 0302-9743 1611-3349 |
| Popis: | Machine Learning (ML) models are very effective in many learning tasks, due to the capability to extract meaningful information from large data sets. Nevertheless, there are learning problems that cannot be easily solved relying on pure data, e.g. scarce data or very complex functions to be approximated. Fortunately, in many contexts domain knowledge is explicitly available and can be used to train better ML models. This paper studies the improvements that can be obtained by integrating prior knowledge when dealing with a context-specific, non-trivial learning task, namely precision tuning of transprecision computing applications. The domain information is injected in the ML models in different ways: I) additional features, II) ad-hoc graph-based network topology, III) regularization schemes. The results clearly show that ML models exploiting problem-specific information outperform the data-driven ones, with an average improvement around 38%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|