In a world and industry which is becoming more commercialised, over sanitised, robotic, structured and predictable, Tyler's greatest strength is the opposite to all of that." That's quite the sell for Southampton's 19-year-old midfield star Tyler Dibling, especially given his basic Premier League career numbers amount to 25 appearances, 1540 minutes played, two goals and zero assists. But that gushing description from one senior source at the club, speaking to BBC Sport anonymously, hints at an emerging talent interesting a host of top clubs and why there are some unsubstantiated reports of a 100m price tag on his head. With the Saints facing an immediate relegation back to the Championship, Dibling's future is likely to be one of the summer's more interesting sagas, with Manchester United, Arsenal, Tottenham and Bayern Munich all reportedly chasing his signature. Another source close to the club suggested Southampton turned down previously unreported bids of 35m from Tottenham and 30m from RB Leipzig in January, with the club valuing Dibling at 55m at the start of the winter window. Southampton have not commented on those rumours, but what is known is that Dibling is one of the lowest paid players in Southampton's squad and has a deal that expires in 2027, after Southampton triggered a 12-month extension option. He signed his last contract in December 2023, when he had played just five minutes of senior football. The England Under-21 international has so far resisted the club's offers of a new deal in what has been a breakthrough season for him, despite a wretched campaign which could still see Southampton relegated with the Premier League's lowest ever points total. His dribbles completed per game (2.34) and fouls won per game (2.57) place him in the top 10. "He's the most fearless player I've ever worked with," former Saints Under-21 head coach Adam Asghar tells BBC Sport. "He's totally unique to anything I've seen before.

Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises like a human? We tested how well the representations of 86 pretrained neural network models mapped to human learning trajectories across two tasks where humans had to learn continuous relationships and categories of natural images. In these tasks, both human participants and neural networks successfully identified the relevant stimulus features within a few trials, demonstrating effective generalisation. We found that while training dataset size was a core determinant of alignment with human choices, contrastive training with multi-modal data (text and imagery) was a common feature of currently publicly available models that predicted human generalisation. Intrinsic dimensionality of representations had different effects on alignment for different model types. Lastly, we tested three sets of human-aligned representations and found no consistent improvements in predictive accuracy compared to the baselines. In conclusion, pretrained neural networks can serve to extract representations for cognitive models, as they appear to capture some fundamental aspects of cognition that are transferable across tasks. Both our paradigms and modelling approach offer a novel way to quantify alignment between neural networks and humans and extend cognitive science into more naturalistic domains.

Often, these changes are driven by different environments or internal states in which the system operates, and we refer to context variables as those variables that indicate this change in causal mechanisms. An example are the causal relations in soil moisture-temperature interactions and their dependence on soil moisture regimes: Dry soil triggers a dependence of soil moisture on latent heat, while environments with wet soil do not feature such a feedback, making it a context-specific property. Crucially, a regime or context variable such as soil moisture need not be exogenous and can be influenced by the dynamical system variables - precipitation can make a dry soil wet - leading to joint systems with endogenous context variables. In this work we investigate the assumptions for constraint-based causal discovery of context-specific information in systems with endogenous context variables. We show that naive approaches such as learning different regime graphs on masked data, or pooling all data, can lead to uninformative results. We propose an adaptive constraint-based discovery algorithm and give a detailed discussion on the connection to structural causal models, including sufficiency assumptions, which allow to prove the soundness of our algorithm and to interpret the results causally. Numerical experiments demonstrate the performance of the proposed method over alternative baselines, but they also unveil current limitations of our method.

It has repeatedly been observed that loss minimization by stochastic gradient descent (SGD) leads to heavy-tailed distributions of neural network parameters. Here, we analyze a continuous diffusion approximation of SGD, called homogenized stochastic gradient descent, and show in a regularized linear regression framework that it leads to an asymptotically heavy-tailed parameter distribution, even though local gradient noise is Gaussian. We give explicit upper and lower bounds on the tail-index of the resulting parameter distribution and validate these bounds in numerical experiments. Moreover, the explicit form of these bounds enables us to quantify the interplay between optimization hyperparameters and the tail-index. Doing so, we contribute to the ongoing discussion on links between heavy tails and the generalization performance of neural networks as well as the ability of SGD to avoid suboptimal local minima.

Understanding the behavior of non-human primates is crucial for improving animal welfare, modeling social behavior, and gaining insights into distinctively human and phylogenetically shared behaviors. However, the lack of datasets on non-human primate behavior hinders in-depth exploration of primate social interactions, posing challenges to research on our closest living relatives. To address these limitations, we present ChimpACT, a comprehensive dataset for quantifying the longitudinal behavior and social relations of chimpanzees within a social group. Spanning from 2015 to 2018, ChimpACT features videos of a group of over 20 chimpanzees residing at the Leipzig Zoo, Germany, with a particular focus on documenting the developmental trajectory of one young male, Azibo. ChimpACT is both comprehensive and challenging, consisting of 163 videos with a cumulative 160,500 frames, each richly annotated with detection, identification, pose estimation, and fine-grained spatiotemporal behavior labels. We benchmark representative methods of three tracks on ChimpACT: (i) tracking and identification, (ii) pose estimation, and (iii) spatiotemporal action detection of the chimpanzees. Our experiments reveal that ChimpACT offers ample opportunities for both devising new methods and adapting existing ones to solve fundamental computer vision tasks applied to chimpanzee groups, such as detection, pose estimation, and behavior analy-37th Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks.

Understanding the behavior of non-human primates is crucial for improving animal welfare, modeling social behavior, and gaining insights into distinctively human and phylogenetically shared behaviors. However, the lack of datasets on non-human primate behavior hinders in-depth exploration of primate social interactions, posing challenges to research on our closest living relatives. To address these limitations, we present ChimpACT, a comprehensive dataset for quantifying the longitudinal behavior and social relations of chimpanzees within a social group. Spanning from 2015 to 2018, ChimpACT features videos of a group of over 20 chimpanzees residing at the Leipzig Zoo, Germany, with a particular focus on documenting the developmental trajectory of one young male, Azibo. ChimpACT is both comprehensive and challenging, consisting of 163 videos with a cumulative 160,500 frames, each richly annotated with detection, identification, pose estimation, and fine-grained spatiotemporal behavior labels.

Machine learning models are widely used in applications where reliability and robustness are critical. Model evaluation often relies on single-point estimates of performance metrics such as accuracy, F1 score, or mean squared error, that fail to capture the inherent variability in model performance. This variability arises from multiple sources, including train-test split, weights initialization, and hyperparameter tuning. Investigating the characteristics of performance metric distributions, rather than focusing on a single point only, is essential for informed decision-making during model selection and optimization, especially in high-stakes settings. How does the performance metric vary due to intrinsic uncertainty in the selected modeling approach? For example, train-test split is modified, initial weights for optimization are modified or hyperparameter tuning is done using an algorithm with probabilistic nature? This is shifting the focus from identifying a single best model to understanding a distribution of the performance metric that captures variability across different training conditions. By running multiple experiments with varied settings, empirical distributions of performance metrics can be generated. Analyzing these distributions can lead to more robust models that generalize well across diverse scenarios. This contribution explores the use of quantiles and confidence intervals to analyze such distributions, providing a more complete understanding of model performance and its uncertainty. Aimed at a statistically interested audience within the machine learning community, the suggested approaches are easy to implement and apply to various performance metrics for classification and regression problems. Given the often long training times in ML, particular attention is given to small sample sizes (in the order of 10-25).

The KLM approach to defeasible reasoning introduces a weakened form of implication into classical logic. This allows one to incorporate exceptions to general rules into a logical system, and for old conclusions to be withdrawn upon learning new contradictory information. Standpoint logics are a group of logics, introduced to the field of Knowledge Representation in the last 5 years, which allow for multiple viewpoints to be integrated into the same ontology, even when certain viewpoints may hold contradicting beliefs. In this paper, we aim to integrate standpoints into KLM propositional logic in a restricted setting. We introduce the logical system of Defeasible Restricted Standpoint Logic (DRSL) and define its syntax and semantics. Specifically, we integrate ranked interpretations and standpoint structures, which provide the semantics for propositional KLM and propositional standpoint logic respectively, in order to introduce ranked standpoint structures for DRSL. Moreover, we extend the non-monotonic entailment relation of rational closure from the propositional KLM case to the DRSL case. The main contribution of this paper is to characterize rational closure for DRSL both algorithmically and semantically, showing that rational closure can be characterized through a single representative ranked standpoint structure. Finally, we conclude that the semantic and algorithmic characterizations of rational closure are equivalent, and that entailment-checking for DRSL under rational closure is in the same complexity class as entailment-checking for propositional KLM.

Visually impaired people are a large group who can only use braille for reading and writing. However, the lack of special educational resources is the bottleneck for educating them. Educational equity is a reflection of the level of social civilization, cultural equality, and individual dignity. Facilitating and improving lifelong learning channels for the visually impaired is of great significance. Their written braille homework or exam papers cannot be understood by sighted teachers, because of the lack of a highly accurate braille translation system, especially in Chinese which has tone marks. braille writers often omit tone marks to save space, leading to confusion when braille with the same consonants and vowels is translated into Chinese. Previous algorithms were insufficient in extracting contextual information, resulting in low accuracy of braille translations into Chinese. This project informatively fine-tuned the mT5 model with an Encoder-decoder architecture for braille to Chinese character conversion. This research created a training set of braille and corresponding Chinese text from the Leipzig Corpora. This project significantly reduced the confusion in braille, achieving $62.4$ and $62.3$ BLEU scores in the validation and test sets, with a curriculum learning fine-tuning method. By incorporating the braille recognition algorithm, this project is the first publicly available braille translation system and can benefit lots of visually impaired students and families who are preparing for the Chinese College Test and help to propel their college dreams in the future. There is a demo on our homepage\footnote{\url{https://vision-braille.com/}}.

Solving the Traveling Salesperson Problem (TSP) remains a persistent challenge, despite its fundamental role in numerous generalized applications in modern contexts. Heuristic solvers address the demand for finding high-quality solutions efficiently. Among these solvers, the Lin-Kernighan-Helsgaun (LKH) heuristic stands out, as it complements the performance of genetic algorithms across a diverse range of problem instances. However, frequent timeouts on challenging instances hinder the practical applicability of the solver. Within this work, we investigate a previously overlooked factor contributing to many timeouts: The use of a fixed candidate set based on a tree structure. Our investigations reveal that candidate sets based on Hamiltonian circuits contain more optimal edges. We thus propose to integrate this promising initialization strategy, in the form of POPMUSIC, within an efficient restart version of LKH. As confirmed by our experimental studies, this refined TSP heuristic is much more efficient - causing fewer timeouts and improving the performance (in terms of penalized average runtime) by an order of magnitude - and thereby challenges the state of the art in TSP solving.