Toward Building Science Discovery Machines

Abstract

The dream of building machines that can do science has inspired scientists for decades. Remarkable advances have been made recently; however, we are still far from achieving this goal. In this paper, we focus on the scientific discovery process where a high level of reasoning and remarkable problem-solving ability are required. We review different machine learning techniques used in scientific discovery with their limitations. We survey and discuss the main principles driving the scientific discovery process. These principles are used in different fields and by different scientists to solve problems and discover new knowledge. We provide many examples of the use of these principles in different fields such as physics, mathematics, and biology. We also review AI systems that attempt to implement some of these principles. We argue that building science discovery machines should be guided by these principles as an alternative to the dominant approach of current AI systems that focuses on narrow objectives. Building machines that fully incorporate these principles in an automated way might open the doors for many advancements.

References in corpus (10)

• Deep Learning: A Critical Appraisal
• Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
• Abstraction and Analogy-Making in Artificial Intelligence
• Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
• Analysing Mathematical Reasoning Abilities of Neural Models
• Learning to Make Analogies by Contrasting Abstract Relational Structure
• Learning Perceptual Inference by Contrasting
• RAVEN: A Dataset for Relational and Analogical Visual rEasoNing
• The General Theory of General Intelligence: A Pragmatic Patternist Perspective
• Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm