Artificial intelligence unmasks anonymous chess players

Software that identifies unique styles poses privacy risks

Solve the Problem of Chess Board in the Shape of the Letter L with Three different Patterns Using Artificial Intelligence & Algorithms

In recent years, the chess game has begun to develop successful programming solutions. Computers were programmed to play chess in the middle of the twentieth century. Computer skills have become better and higher than the skills of chess players in the world, and from here this study has made it possible to find the optimal solution for the four square pieces in the form of a letter (L) without repetition and quick access to fill the sites and voids and to complete the entire area. It is our task to cover a (2n×2n) Chessboard with L-shaped tiles each tile is a (2×2) square with a (1×1) square removed from one corner. We are working to cover the Chessboard in such a way that there is a single 1×1 box left in the ‘corner’ of the Chessboard (by the 'corner' we mean one corner of the box should be uncovered). In this task, we will solve this problem with three approaches, the C programming approach, the second by dividing and conquering approach and the last by a greedy method approach. Three algorithms were used and a comparison was made between them, and the fastest method was achieved by a greedy method, with eight cases comparing one and four cases, respectively.

The meta-analyses of deliberate practice underestimate the effect size because they neglect the core characteristic of individualization—an analysis and empirical evidence

Influential meta-analyses have concluded that only a small to medium proportion of variance in performance can be explained by deliberate practice. We argue that the authors have neglected the most important characteristic of deliberate practice: individualization of practice. Many of the analyzed effect sizes derived from measures that did not assess individualized practice and, therefore, should not have been included in meta-analyses of deliberate practice. We present empirical evidence which suggests that the level of individualization and quality of practice (indicated by didactic educational capital) substantially influences the predictive strength of practice measures. In our study of 178 chess players, we found that at a high level of individualization and quality of practice, the effect size of structured practice was more than three times higher than that found at the average level. Our theoretical analysis, along with empirical results, support the claim that the explanatory power of deliberate practice has been considerably underestimated in the meta-analyses. The question of how important deliberate practice is for individual differences in performance remains an open question.

Formation of Intellectual Activity of Primary Schoolchildren in the Process of Learning to Play Chess

The purpose of the article is the solution of the problem of activating the intelligence of students, it seems especially relevant as an innovative technological stage that promotes young chess players to a higher level of realization of creative inclinations and abilities, intellectual potential. The following methods are used in the learning process: observation, testing, conversation, game methods, methods for solving chess problems, writing games, designing and solving original chess problems, modern information technologies, participation in competitions, including the Internet competitions, viewing and analyzing the content of chess games, participation in tournaments and competitions, P. Torrens creativity test «Finish a painting». Results. The Torrence test, conducted at the beginning and at the end of the study, determined the effectiveness of the experiment. We got a result that differs from the initial one: if the number of children with a low level was 27%, then at the final stage up to 19%, some of them moved to the middle level, some went to the group with a high level. The number of students with a high level at the beginning – 12%, at the end of the experiment – 21%. Conclusions. The intellectual activity of younger schoolchildren in the process of learning to play chess suggests that the student demonstrates the ability to break from the traditional solution and type of tasks to another type of tasks – original, non-standard, having a different proof algorithm, significantly improves the quality of training of young chess players, activates mental activity. The main thing is the active internal activity of the child himself, the realization of intellectual abilities, the development of inclinations, their transformation into intellectual abilities, unconventional, contradictory, creative thinking, the presence of a life goal to achieve chess heights, which determines his further own nature of activity.

CHESS RESEARCH: RECENT TRENDS

Considerable research has been carried out on chess in the last seventy years. While classic research has centred on perception, memory, and decision making, contemporary research has focused on deliberate practice, individual differences, and education. Contrasting with classical research, which has mainly used experiments and computer modelling, more recent research has tended to use questionnaires, interviews, and analysis of computer databases as source of information. This article reviews these recent research trends, focusing on what has been learnt from chess research with respect to deliberate practice, intelligence, and transfer of skill. It also discusses ageing and risk taking between civilizations as examples of computer database analyses. Results clearly indicate that deliberate practice is a necessary, but not sufficient condition for achieving high levels of expertise. Other factors are important, some of which are innate. One of them is intelligence. Data show that chess players on average are more intelligent than individuals who do not play chess, and that chess skill positively correlates with intelligence. These results are unlikely to be explained by the hypothesis that chess leads to an increase of intelligence, as the results of experiments using chess instruction to bring about far-transfer effects are inconsistent. In addition, experiment designs used in chess instruction research are typically insufficient to allow strong conclusions about causality. Research using chess databases have led to interesting results, but its generalisability is likely to be limited. The article ends with recommendations for future research.

Predicting Problem Difficulty in Chess

We investigate the question of automatic prediction of task difficulty for humans, of problems that are typically solved through informed search. Our experimental domain is the game of chess. We analyse experimental data from human chess players solving tactical chess problems. The players also estimated the difficulty of these problems. We carried out an experiment with an approach to automatically estimate the difficulty of problems in this domain. The idea of this approach is to use the properties of a “meaningful search tree” to learn to estimate the difficulty of example problems. The construct of a meaningful search tree is an attempt at approximating problem solving by human experts. The learned difficulty classifier was applied to our experimental problems, and the resulting difficulty estimates matched well with the measured difficulties on the Chess Tempo website, and also with the average difficulty perceived by the players.

Professional Chess Expertise Modulates Whole Brain Functional Connectivity Pattern Homogeneity and Couplings

Previous studies have revealed changed functional connectivity patterns between brain areas in chess players using resting-state functional magnetic resonance imaging (rs-fMRI). However, how to exactly characterize the voxel-wise whole brain functional connectivity pattern changes in chess players remains unclear, which could provide more convincing evidence for establishing the relationship between long-term chess practice and brain function changes. In this study, we employed newly developed whole brain functional connectivity pattern homogeneity (FcHo) method to identify the voxel-wise changes of functional connectivity patterns in 28 chess master players and 27 healthy novices. Seed-based functional connectivity analysis was used to identify the alteration of corresponding functional couplings. FcHo analysis revealed significantly increased whole brain functional connectivity pattern similarity in anterior cingulate cortex (ACC), anterior middle temporal gyrus (aMTG), primary visual cortex (V1), and decreased FcHo in thalamus and precentral gyrus in chess players. Resting-state functional connectivity analyses identified chess players showed decreased functional connections between V1 and precentral gyrus. Besides, a linear support vector machine (SVM) based classification achieved an accuracy of 85.45%, a sensitivity of 85.71% and a specificity of 85.19% to differentiate chess players from novices by leave-one-out cross-validation. Finally, correlation analyses revealed that the mean FcHo values of thalamus were significantly negatively correlated with the training time. Our findings provide new evidences for the important roles of ACC, aMTG, V1, thalamus and precentral gyrus in chess players and indicate that long-term professional chess training may enhance the semantic and episodic processing, efficiency of visual-motor transformation, and cognitive ability.

Determining Chess Game State from an Image

Identifying the configuration of chess pieces from an image of a chessboard is a problem in computer vision that has not yet been solved accurately. However, it is important for helping amateur chess players improve their games by facilitating automatic computer analysis without the overhead of manually entering the pieces. Current approaches are limited by the lack of large datasets and are not designed to adapt to unseen chess sets. This paper puts forth a new dataset synthesised from a 3D model that is an order of magnitude larger than existing ones. Trained on this dataset, a novel end-to-end chess recognition system is presented that combines traditional computer vision techniques with deep learning. It localises the chessboard using a RANSAC-based algorithm that computes a projective transformation of the board onto a regular grid. Using two convolutional neural networks, it then predicts an occupancy mask for the squares in the warped image and finally classifies the pieces. The described system achieves an error rate of 0.23% per square on the test set, 28 times better than the current state of the art. Further, a few-shot transfer learning approach is developed that is able to adapt the inference system to a previously unseen chess set using just two photos of the starting position, obtaining a per-square accuracy of 99.83% on images of that new chess set. The code, dataset, and trained models are made available online.