Machine Learning in the Next Five Years

By Donald Michie. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Isaac Lage
2. Menaka Narayanan
3. Been Kim
4. Emily Chen
5. Finale Doshi-Velez
6. Jeffrey He
7. Samuel J. Gershman
8. Giulia Vilone

Citations in the corpus

• What Does Explainable AI Really Mean? A New Conceptualization of Perspectives (2017, background): “A comprehensible system emits symbols along with its output (echoing Michie’s strong and ultra-strong machine learning [11]).”
• How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation (2018, background): “While interpretability has a long history in AI [Michie, 1988], the relatively recent widespread adoption of machine learning systems in real, complex environments has lead to an increased attention to interpretable machine learning systems, with applications including understanding notifications on”
• How Does Predicate Invention Affect Human Comprehensibility? (2016, unknown): “In the late 1980s Michie [8] suggested the idea of using both comprehensibility of hypotheses and predictive accuracy as performance indicators for Machine Learning.”
• An Evaluation of the Human-Interpretability of Explanation (2019, background): “While interpretability has a long history in AI [Michie, 1988], the relatively recent widespread adoption of machine learning systems in real, complex environments has lead to an increased attention to interpretable machine learning systems, with applications including understanding notifications on”
• A historical perspective of explainable Artificial Intelligence (2020, background): “3 The categorization of explanations based on the type of system (sub-symbolic, symbolic, and hybrid) also relates to Michie (1988)'s criteria for machine learning: weak, strong and ultra-strong.”