The Value Learning Problem
نویسنده
چکیده
Autonomous AI systems’ programmed goals can easily fall short of programmers’ intentions. Even a machine intelligent enough to understand its designers’ intentions would not necessarily act as intended. We discuss early ideas on how one might design smarter-than-human AI systems that can inductively learn what to value from labeled training data, and highlight questions about the construction of systems that model and act upon their operators’ preferences.
منابع مشابه
Fuzzy Multi-objective Permutation Flow Shop Scheduling Problem with Fuzzy Processing Times under Learning and Aging Effects
In industries machine maintenance is used in order to avoid untimely machine fails as well as to improve production effectiveness. This research regards a permutation flow shop scheduling problem with aging and learning effects considering maintenance process. In this study, it is assumed that each machine may be subject to at most one maintenance activity during the planning horizon. The objec...
متن کاملProblem-Based and Lecture-Based Methods Compared: The Mediating Role of Perceptual Control and Value Cognition
It is necessary to clarify factors affecting student emotions as they play an important role in their learning. Among such factors teaching method looms large, and given the variety of methods used, a comparison of these methods in terms of their relation to things like perceptual control and value cognition, can lead to a better choice in regards to helping the students learn better....
متن کاملThe Effect of Problem-Based Learning Clinical Education on Nursing Student's Critical Thinking
Background: Problem-based clinical education is an effective strategy for enhancing creativity, group work, leadership and problem-solving skills in nursing students. It seems PBL can improve nursing students’ critical thinking skills. The aim of this study was to investigate the effects of problem-based clinical education on nursing students’ critical thinking. Methods: This randomized control...
متن کاملLecturing or Problem-based Learning: Comparing Effects of the Two Teaching Methods in Academic Achievement and Knowledge Retention in Pediatrics Course for Nursing Students
Introduction: Using the appropriate teaching methods, nursing educators are trying to improve students` both effective learning and knowledge retention. The survey reveals the impact of lecturing and problem-based learning in academic achievement and knowledge retention in the pediatrics course. Methods: A quasi-experimental design was used to compare the effects of the two teaching methods. ...
متن کاملA Hybrid Optimization Algorithm for Learning Deep Models
Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...
متن کاملA Hybrid Optimization Algorithm for Learning Deep Models
Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...
متن کامل