Regulating Accuracy-Efficiency Trade-Offs in Distributed Machine Learning Systems

We consider the question: what is the abstraction that should be implemented by the computational engine of a machine learning system? Current machine learning systems typically push whole tensors through a series of compute kernels such as matrix multiplications or activation functions, where each kernel runs on an AI accelerator (ASIC) such as a GPU. This implementation abstraction provides little built-in support for ML systems to scale past a single machine, or for handling large models with matrices or tensors that do not easily fit into the RAM of an ASIC. In this paper, we present an alternative implementation abstraction called the tensor relational algebra (TRA). The TRA is a set-based algebra based on the relational algebra. Expressions in the TRA operate over binary tensor relations, where keys are multi-dimensional arrays and values are tensors. The TRA is easily executed with high efficiency in a parallel or distributed environment, and amenable to automatic optimization. Our empirical study shows that the optimized TRA-based back-end can significantly outperform alternatives for running ML workflows in distributed clusters.

Download Full-text

Platform for Analysing and Encouraging Student Activity on Contest and E-learning Systems

OLYMPIADS IN INFORMATICS ◽

10.15388/ioi.2018.07 ◽

2018 ◽

Vol 12 ◽

pp. 85-98

Author(s):

Bojan Kostadinov ◽

Mile Jovanov ◽

Emil STANKOV

Keyword(s):

Machine Learning ◽

Data Collection ◽

Educational Policy ◽

Learning Systems ◽

Data Sources ◽

Or Education ◽

Student Activity ◽

The World ◽

E Learning ◽

Analyse Data

Data collection and machine learning are changing the world. Whether it is medicine, sports or education, companies and institutions are investing a lot of time and money in systems that gather, process and analyse data. Likewise, to improve competitiveness, a lot of countries are making changes to their educational policy by supporting STEM disciplines. Therefore, it’s important to put effort into using various data sources to help students succeed in STEM. In this paper, we present a platform that can analyse student’s activity on various contest and e-learning systems, combine and process the data, and then present it in various ways that are easy to understand. This in turn enables teachers and organizers to recognize talented and hardworking students, identify issues, and/or motivate students to practice and work on areas where they’re weaker.

Download Full-text

Predicting Undesired Treatment Outcome in Mental Healthcare: Machine Learning Study (Preprint)

10.2196/preprints.17235 ◽

2019 ◽

Author(s):

Kasper Van Mens ◽

Joran Lokkerbol ◽

Richard Janssen ◽

Robert de Lange ◽

Bea Tiemens

Keyword(s):

Machine Learning ◽

Treatment Outcome ◽

Mental Health Treatment ◽

Mental Healthcare ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Trade Off ◽

Trade Offs ◽

Outcome Monitoring ◽

Extreme Gradient Boosting

BACKGROUND It remains a challenge to predict which treatment will work for which patient in mental healthcare. OBJECTIVE In this study we compare machine algorithms to predict during treatment which patients will not benefit from brief mental health treatment and present trade-offs that must be considered before an algorithm can be used in clinical practice. METHODS Using an anonymized dataset containing routine outcome monitoring data from a mental healthcare organization in the Netherlands (n = 2,655), we applied three machine learning algorithms to predict treatment outcome. The algorithms were internally validated with cross-validation on a training sample (n = 1,860) and externally validated on an unseen test sample (n = 795). RESULTS The performance of the three algorithms did not significantly differ on the test set. With a default classification cut-off at 0.5 predicted probability, the extreme gradient boosting algorithm showed the highest positive predictive value (ppv) of 0.71(0.61 – 0.77) with a sensitivity of 0.35 (0.29 – 0.41) and area under the curve of 0.78. A trade-off can be made between ppv and sensitivity by choosing different cut-off probabilities. With a cut-off at 0.63, the ppv increased to 0.87 and the sensitivity dropped to 0.17. With a cut-off of at 0.38, the ppv decreased to 0.61 and the sensitivity increased to 0.57. CONCLUSIONS Machine learning can be used to predict treatment outcomes based on routine monitoring data.This allows practitioners to choose their own trade-off between being selective and more certain versus inclusive and less certain.

Download Full-text