Related Experiment Videos
Explainable AI: learning from the learners
Ricardo Vinuesa1, Steven L Brunton2, Gianmarco Mengaldo3
1Department of Aerospace Engineering, University of Michigan, Ann Arbor, USA. rvinuesa@umich.edu.
Nature Communications
|August 6, 2026
Summary
Explainable artificial intelligence (XAI) helps understand AI decisions in science. Combining XAI with causal reasoning and domain validation allows AI to learn from its own processes, improving discovery and trust.
Area of Science:
- Artificial Intelligence
- Scientific Discovery
- Causal Reasoning
Background:
- AI now surpasses human performance in many scientific and engineering tasks.
- The internal decision-making processes of AI models often lack transparency.
- Opaque AI models hinder trust and accountability in critical applications.
Purpose of the Study:
- To advocate for the use of explainable artificial intelligence (XAI) in scientific research.
- To demonstrate how XAI, causal reasoning, and domain validation can enhance AI's learning capabilities.
- To explore the application of XAI in AI-driven discovery, optimization, and certification.
Main Methods:
- Utilizing foundation models for AI development.
- Applying explainability methods to analyze AI decision processes.
- Integrating causal reasoning and domain validation for robust AI application.
Main Results:
- XAI methods can reveal the internal workings of AI models.
- AI can generate novel mechanistic hypotheses for scientific inquiry.
- Guided design and control processes are improved through AI insights.
- Enhanced trust and accountability in high-stakes AI applications are achievable.
Conclusions:
- Explainable AI is crucial for understanding and trusting AI in science.
- The synergy of XAI, causal reasoning, and domain validation unlocks AI's full potential.
- XAI facilitates AI-assisted scientific discovery, optimization, and certification.
Related Concept Videos
Observational Learning
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...
Associative Learning
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
Non-equilibrium in the Cell
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
Purposive Learning
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a bonus...
Cognitive Learning
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Introduction to Learning
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...