Silas, is a generic data mining and predictive analytics software toolkit built upon advanced machine learning, automated reasoning and artificial intelligence techniques. It deals with any type of structured data and performs tasks such as classification, regression, segmentation, anomaly detection, prediction, and more.
This paper introduces Silas as a high-performance machine learning tool, which is built to provide a more transparent, dependable and efficient data analytics service. We discuss the machine learning aspects of Silas and demonstrate the advan- tage of Silas in its predictive and computational performance. We show that several customised algorithms in Silas yield better predictions in a significantly shorter time compared to state-of-the-art. Another focus of Silas is on providing a formal foundation of decision trees to support logical analysis and verification of learned prediction models. We illustrate the potential capabilities of the fusion of machine learning and logical reasoning by showcasing applications in three directions: formal verification of the prediction model against user specifications, training correct-by-construction models, and explaining the decision-making of predictions.
Silas implements novel tree-based learning algorithms that yield high predictive performance when dealing with structured data.
Silas adopts various high-performance computing techniques to ensure that the computation is fast and memory-efficient. Silas is built to handle big data and it can be deployed on high performance clusters.
Silas uses formal verification techniques to mathematically verify that the prediction model satisfies user specifications. Further, user specifications can be enforced during the training phase.
Silas adopts the latest automated reasoning techniques to reason about the predictive model and provides insights on the rationale behind the decision-making.
Zhe Hou (common: "Zee Ho", correct-ish: "Hojer") was born in Xi'an, one of the most historical cities in the world and a cultural centre of China since 1000 BC. Zhe obtained his PhD from the Australian National University, Canberra, and was a student of Rajeev Gore and Alwen Tiu. Lured by the fantastic food and a job, he moved to Nanyang Technological University, Singapore, in 2015. Planned to settle down in Melbourne, but after a call from Jin Song Dong, he joined Griffith University in 2017 and became a lecturer there in late 2019.
Jin-Song Dong is a full professor at the School of Computing at the National University of Singapore (NUS) and a visiting research professor at Griffith University (part-time). From 2017-2018, Jin Song was the Director of the Institute for Integrated Intelligent Systems (IIIS) at Griffith University and managed to double IIIS external funding in two years. His research is in the areas of formal methods, safety and security systems, probabilistic reasoning, and trusted machine learning. He co-founded PAT verification system which has attracted 4000+ registered users from 1000+ organizations in 150 countries and won 20 Year ICFEM Most Influential System Award in 2018. Jin Song has been on the editorial board of ACM Transaction on Software Engineering and Methodology, Formal Aspects of Computing and Innovations in Systems and Software Engineering, A NASA Journal. He has successfully supervised 26 Ph.D. students and many of them have become tenured faculty https://www.comp.nus.edu.sg/~dongjs/members in the leading universities around the world. He is a Fellow of the Institute of Engineers Australia. In his spare time, he developed Markov Decision Process (MDP) models for tennis strategy analysis in PAT.