21 papers · ranked by Valyu relevance
Hamid R. Tizhoosh, Shahryar Rahnamayan
—The idea of opposition-based learning was introduced 10 years ago. Since then a noteworthy group of researchers has used some notions of oppositeness to improve existing optimization and learning algorithms. Among others, evolutionary algorithms, reinforcement agents, and neural networks have been reportedly extended…
Rihab Lakbichi, Farouq Zitouni, Saad Harous, Aridj Ferhat + 5 more
In recent years, opposition-based learning (OBL) has emerged as a powerful enhancement strategy in metaheuristic algorithms (MAs), gaining significant attention for its potential to accelerate convergence and improve solution quality. Existing research lacks a structured analysis of how different OBL variants influence…
Shivam Kalra, Aditya Sriram, Shahryar Rahnamayan, Hamid R. Tizhoosh
Many research works have successfully extended algorithms such as evolutionary algorithms, reinforcement agents and neural networks using "opposition-based learning" (OBL). Two types of the "opposites" have been defined in the literature, namely type-I and type-II. The former are linear in nature and applicable to the…
Abdesslem Layeb
In this paper, we introduce a novel data transformation framework based on Opposition-Based Learning (OBL) to boost the performance of traditional classification algorithms. Originally developed to accelerate convergence in optimization tasks, OBL is leveraged here to generate synthetic opposite samples that enrich the…
Xuan Xiong, Shaobo Li, Fengbin Wu, Fernando Morgado-Dias
Global optimization problems have been a research topic of great interest in various engineering applications among which neural network algorithm (NNA) is one of the most widely used methods. However, it is inevitable for neural network algorithms to plunge into poor local optima and convergence when tackling complex…
Xueyan Niu, Ho Yin Chau, Tai Sing Lee, Wen-Hao Zhang
Multisensory integration areas such as dorsal medial superior temporal (MSTd) and ventral intraparietal (VIP) areas in macaques combine visual and vestibular cues to produce better estimates of self-motion. Congruent and opposite neurons, two types of neurons found in these areas, prefer congruent inputs and opposite…
Ho Yin Chau, Wen-Hao Zhang, Tai Sing Lee
Opposite neurons, found in macaque dorsal medial superior temporal (MSTd) and ventral intraparietal (VIP) areas, combine visual and vestibular cues of self-motion in opposite ways. A neural circuit recently proposed utilizes opposite neurons to perform causal inference and decide whether the visual and vestibular cues…
Julie Y. L. Chow, Jessica C. Lee, Peter F. Lovibond
Influential models of causal learning assume that learning about generative and preventive relationships are symmetrical to each other. That is, a preventive cue directly prevents an outcome from occurring (i.e., “direct” prevention) in the same way a generative cue directly causes an outcome to occur. However…
Isabelle Dautriche, Brian Buccola, Melissa Berthet, Joel Fagot + 1 more
'Emmanuel Chemla'] Can non-human animals combine abstract representations much like humans do with language? In particular, can they entertain a compositional representation such as ‘not blue’? Across two experiments, we demonstrate that baboons (Papio papio) show a capacity for compositionality. Experiment 1 showed…
Kenji Morita, Kanji Shimomura, Yasuo Kawaguchi
While positive reward prediction errors (RPEs) and negative RPEs have equal impacts in the standard reinforcement learning, the brain appears to have distinct neural pathways for learning mainly from either positive or negative feedbacks, such as the direct and indirect pathways of the basal ganglia (BG). Given that…
Hilary J. Don, Micah B. Goldwater, Evan J. Livesey
In his essay “The Aims of Education,” Alfred North Whitehead ([55]) famously cautioned against “inert ideas.” He argued that an idea that was simply memorized and not used-in the sense of relating it to other ideas or novel situations as they arise-was potentially worse than learning no idea at all. The assumption at…
Brad R. Foley, Paul Marjoram, Sergey V. Nuzhdin, Björn Brembs
The most basic models of learning are reinforcement learning models (for instance, classical and operant conditioning) that posit a constant learning rate; however many animals change their learning rates with experience. This process is sometimes studied by reversing an existing association between cues and rewards…
Erika Branchini, Elena Capitani, Roberto Burro, Ugo Savardi + 1 more
'Ivana Bianchi'] Our aim in this paper is to contribute toward acknowledging the general role of opposites as an organizing principle in the human mind. We support this claim in relation to human reasoning by collecting evidence from various studies which shows that “thinking in opposites” is not only involved in…
Zhe Wu, Kai Li, Hang Xu, Meng Zhang + 3 more
'Junliang Xing'] Opponent modeling is essential to exploit suboptimal opponents in strategic interactions. Most previous works focus on building explicit models to directly predict the opponents' styles or strategies, which require a large amount of data to train the model and lack adaptability to unknown opponents. In…
Niklas H. Kokkola, Esther Mondragón, Eduardo Alonso
In this paper a formal model of associative learning is presented which incorporates representational and computational mechanisms that, as a coherent corpus, empower it to make accurate predictions of a wide variety of phenomena that so far have eluded a unified account in learning theory. In particular, the Double…
Shiva Farashahi, Alireza Soltani
Learning appropriate representations of the reward environment is extremely challenging in the real world where there are many options to learn about and these options have many attributes or features. Despite existence of alternative solutions for this challenge, neural mechanisms underlying emergence and adoption of…
Anestis Fachantidis, Matthew E. Taylor, Ioannis Vlahavas
—In this article we study the transfer learning model of action advice under a budget. We focus on reinforcement learning teachers providing action advice to heterogeneous students playing the game of Pac-Man under a limited advice budget. First, we examine several critical factors affecting advice quality in this…
Yannick Ureel, Maarten R. Dobbelaere, Yi Ouyang, Kevin De Ras + 3 more
By combining machine learning with design of experiments, so-called active machine learning, more efficient and cheaper research can be conducted. Machine learning algorithms are more flexible, and are better at investigating the processes spanning all length scales of chemical engineering. While the active machine…
Paul Francoeur, Daniel Penaherrera, David Koes
The immense size of chemical space, the relative scarcity of high quality data, and the cost of running experiments to accurately measure molecular properties makes active learning (AL) an attractive approach to efficiently explore the space and train high-quality models for molecular property prediction. While AL is…
Aylin Apostel, Jonas Rose
Grouping objects into discrete categories affects how we perceive the world and represents a crucial element of cognition. Categorization is a widespread phenomenon that has been thoroughly studied. However, investigating categorization learning poses several requirements on the stimulus set in order to control which…
Authors not listed
In philosophy and science, a first principle is a basic proposition or assumption that cannot be deduced from any other proposition or assumption. Ancient Greek philosophy Aristotle defined the first principle as “the first basis from which a thing is known.” First principles thinking (or reasoning from first…