Future Directions in Machine Learning

Abstract

Current machine learning (ML) algorithms identify statistical regularities in complex data sets and are regularly used across a range of application domains, but they lack the robustness and generalizability associated with human learning. If ML techniques could enable computers to learn from fewer examples, transfer knowledge between tasks, and adapt to changing contexts and environments, the results would have very broad scientific and societal impacts. Increased processing and memory resources have enabled larger, more capable learning models, but there is growing recognition that even greater computing resources would not be sufficient to yield algorithms capable of learning from a few examples and generalizing beyond initial training sets. This paper presents perspectives on feature selection, representation schemes and interpretability, transfer learning, continuous learning, and learning and adaptation in time-varying contexts and environments, five key areas that are essential for advancing ML capabilities. Appropriate learning tasks that require these capabilities can demonstrate the strengths of novel ML approaches that could address these challenges.