We introduce a recursive AlphaZero-style Monte--Carlo tree search algorithm, "RMCTS". The advantage of RMCTS over AlphaZero's MCTS-UCB is speed. In RMCTS, the search tree is explored in a breadth-first manner, so that network inferences naturally occur in large batches. This significantly reduces the GPU latency cost. We find that RMCTS is often more than 40 times faster than MCTS-UCB when searching a single root state, and about 3 times faster when searching a large batch of root states. The recursion in RMCTS is based on computing optimized posterior policies at each game state in the search tree, starting from the leaves and working back up to the root. Here we use the posterior policy explored in "Monte--Carlo tree search as regularized policy optimization" (Grill, et al.) Their posterior policy is the unique policy which maximizes the expected reward given estimated action rewards minus a penalty for diverging from the prior policy. The tree explored by RMCTS is not defined in an adaptive manner, as it is in MCTS-UCB. Instead, the RMCTS tree is defined by following prior network policies at each node. This is a disadvantage, but the speedup advantage is more significant, and in practice we find that RMCTS-trained networks match the quality of MCTS-UCB-trained networks in roughly one-third of the training time. We include timing and quality comparisons of RMCTS vs. MCTS-UCB for three games: Connect-4, Dots-and-Boxes, and Othello.
Ahmed Alzahrani, Muhammad Ali Raza, Muhammad Zubair Asghar
As per a WHO survey conducted in 2023, more than 2.3 million breast cancer (BC) cases are reported every year. In nearly 95% of countries, the second leading cause of death for females is BC. Breast and cervical cancers cause 80% of reported deaths in middle-income countries. Early detection of breast cancer can help patients better manage their condition and increase their chances of survival. However, traditional AI models frequently conceal their decision-making processes and are mainly tailored for classification tasks. Our approach combines composite deep learning techniques with explainable artificial intelligence (XAI) to enhance interpretability and predictive accuracy. By utilizing XAI to examine features and provide insights into its classifications, the model clarifies the rationale behind its decisions, resulting in an understanding of concealed patterns linked to breast cancer detection. The XAI strengthens practitioners’ and health researchers’ confidence and understanding of artificial intelligence (AI)-based models. In this work, we introduce a hybrid deep learning bi-directional long short-term memory-convolutional neural network (BiLSTM-CNN) model to identify breast cancer using patient data effectively. We first balanced the dataset before using the BiLSTM-CNN model. The hybrid deep learning (DL) model presented here performed well in comparison to other studies, with 0.993 accuracy, precision 0.99, recall 0.99, and F1-score 0.99.
This short paper is a primer on the nature of state sovereignty and the importance of claims about it. It also aims to reveal (merely reveal) a strategy for working with vague or contradictory data about which states, in fact, are sovereign. These goals together are intended to set the stage for applied work in ontology about international affairs.
The development of large language models (LLMs) is limited by a lack of explainability, the absence of a unifying theory, and prohibitive operational costs. We propose a neuro-theoretical framework for the emergence of intelligence in systems that is both functionally robust and biologically plausible. The model provides theoretical insights into cognitive processes such as decision-making and problem solving, and a computationally efficient approach for the creation of explainable and generalizable artificial intelligence.
We give a simple Schönhage Storage Modification Machine that simulates one iteration of the Rule 110 cellular automaton. This provides an alternative construction to Schönhage's original proof of the Turing completeness of the eponymous machines.
Carbon disulfide, an important sulfur-containing species, has strong absorption lines in the wavelength range of 188 nm to 215 nm. It is difficult to accurately measure the absorption cross sections of carbon disulfide because carbon disulfide will be easily converted into carbon sulfide when it is exposed to ultraviolet light. In this study, the absorption cross sections of carbon disulfide were measured by reducing carbon disulfide conversion. The factors affecting carbon disulfide conversion, including gas flow rate, ultraviolet light intensity, and duration of illumination, were studied to reduce the conversion of carbon disulfide by controlling experimental conditions in the experiment. Finally, the absorption cross sections of carbon disulfide at room temperature and atmospheric pressure were calculated using the absorption spectrum and the carbon disulfide concentration in the absence of carbon disulfide conversion. The wavelengths of 16 absorption peaks on the carbon disulfide absorption cross sections of the vibration change were marked. Carbon disulfide has the maximum absorption cross section of 4.5 × 10–16 cm2/molecule at a wavelength of 198.10 nm.
We introduce a framework for reaching a consensus amongst several agents communicating via a trust network on conflicting information about their environment. We formalise our approach and provide an empirical and theoretical analysis of its properties.
The Cognitive Theory of True Conditions (CTTC) is a proposal to design the implementation of cognitive abilities and to describe the model-theoretic semantics of symbolic cognitive architectures. The CTTC is formulated mathematically using the multi-optional many-sorted past present future(MMPPF) structures. This article discussed how decision-making processes are described in the CTTC.
In this paper $\ast$--compatible extensions of fuzzy relations are studied, generalizing some results obtained by Duggan in case of crisp relations. From this general result are obtained as particular cases fuzzy versions of some important extension theorems for crisp relations (Szpilrajn, Hansson, Suzumura). Two notions of consistent closure of a fuzzy relation are introduced.
We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000).
The article is dedicated to the analysis of the existing models for assessment based of the fuzzy logic centroid technique. A new Generalized Rectangular Model were developed. Some generalizations of the existing models are offered.
The paper attempts to describe the space of possible mind designs by first equating all minds to software. Next it proves some interesting properties of the mind design space such as infinitude of minds, size and representation complexity of minds. A survey of mind design taxonomies is followed by a proposal for a new field of investigation devoted to study of minds, intellectology, a list of open problems for this new field is presented.
We introduce in this paper an algorithm named Contextuel-E-Greedy that tackles the dynamicity of the user's content. It is based on dynamic exploration/exploitation tradeoff and can adaptively balance the two aspects by deciding which situation is most relevant for exploration or exploitation. The experimental results demonstrate that our algorithm outperforms surveyed algorithms.
In this paper, concept of possibility neutrosophic soft set and its operations are defined, and their properties are studied. An application of this theory in decision making is investigated. Also a similarity measure of two possibility neutrosophic soft sets is introduced and discussed. Finally an application of this similarity measure is given to select suitable person for position in a firm.
This is a working paper summarizing results of an ongoing research project whose aim is to uniquely characterize the uncertainty measure for the Dempster-Shafer Theory. A set of intuitive axiomatic requirements is presented, some of their implications are shown, and the proof is given of the minimality of recently proposed measure AU among all measures satisfying the proposed requirements.
Modification of a conceptual clustering algorithm Cobweb for the purpose of its application for numerical data is offered. Keywords: clustering, algorithm Cobweb, numerical data, fuzzy membership function.
A modelling language is described which is suitable for the correlation of information when the underlying functional model of the system is incomplete or uncertain and the temporal dependencies are imprecise. An efficient and incremental implementation is outlined which depends on cost functions satisfying certain criteria. Possibilistic logic and probability theory (as it is used in the applications targetted) satisfy these criteria.
This file summarizes the plenary talk on laboratory experiments on logic at the TARK 2013 - 14th Conference on Theoretical Aspects of Rationality and Knowledge.
This paper takes new look on language and knowledge modelling for corpus linguistics. Using ideas of Chaitin, a line of argument is made against language/knowledge separation in Natural Language Processing. A simplistic model, that generalises approaches to language and knowledge, is proposed. One of hypothetical consequences of this model is Strong AI.