In pattern recognition, a random label Y is to be predicted based upon observing a random vector X valued in $\mathbb{R}^d$ with d> 1 by means of a classification rule with minimum probability of error.

Working memory, or the ability to hold and manipulate information in the mind, is a critical component of human intelligence and executive functioning. It is correlated with performance on various cognitive tasks, including measures of fluid intelligence, which encompasses reasoning and problem solving. We use a comprehensive set of classic working memory tasks to estimate the working memory capacity of large language models (LLMs). We find that in most cases, LLMs exceed normative human scores. However, we do not find that the increased capacity of working memory is associated with higher performance on other executive functioning tasks or problem solving benchmarks. These results suggest that LLMs may have deficits in attentional control and cognitive flexibility, which result in difficulties with inhibiting automatic responses and adapting to shifting information. Our findings suggest that current reasoning models have mixed results in compensating for these deficits.

In pattern recognition, a random label Y is to be predicted based upon observing a random vector X valued in $\mathbb{R}^d$ with d> 1 by means of a classification rule with minimum probability of error.

Contrarily to the entropy functional, the DC score is extremely tractable.

A.1 Upper bound for stochastic gradient descent This subsection is devoted to the proof of Theorem 1. Convergence of stochastic gradient descent for non-smooth problems is a known result. For completeness, we reproduce and adapt a usual proof to our setting. This corresponds to the gradient written in Algorithm 1. For resampling strategies, the proof is built on classical statistical learning theory considerations. Let us begin by controlling the estimation error.

Supervised classification techniques use training samples to find classification rules with small expected 0-1 loss. Conventional methods ac hieve efficient learning and out-of-sample generalization by minimizing surrog ate losses over specific families of rules. This paper presents minimax risk classifi ers (MRCs) that do not rely on a choice of surrogate loss and family of rules. MRCs ac hieve efficient learning and out-of-sample generalization by minimizing w orst-case expected 0-1 loss w.r.t.

We present a new approach to classification that combines data and knowledge. In this approach, data mining is used to derive association rules (possibly with negations) from data. Those rules are leveraged to increase the predictive performance of tree-based models (decision trees and random forests) used for a classification task. They are also used to improve the corresponding explanation task through the generation of abductive explanations that are more general than those derivable without taking such rules into account. Experiments show that for the two tree-based models under consideration, benefits can be offered by the approach in terms of predictive performance and in terms of explanation sizes.

We present a new approach for distilling boosted trees into decision trees, in the objective of generating an ML model offering an acceptable compromise in terms of predictive performance and interpretability. We explain how the correction approach called rectification can be used to implement such a distillation process. We show empirically that this approach provides interesting results, in comparison with an approach to distillation achieved by retraining the model.

Boosting methods often achieve excellent classification accuracy, but can experience notable performance degradation in the presence of label noise. Existing robust methods for boosting provide theoretical robustness guarantees for certain types of label noise, and can exhibit only moderate performance degradation. However, previous theoretical results do not account for realistic types of noise and finite training sizes, and existing robust methods can provide unsatisfactory accuracies, even without noise. This paper presents methods for robust minimax boosting (RMBoost) that minimize worst-case error probabilities and are robust to general types of label noise. In addition, we provide finite-sample performance guarantees for RMBoost with respect to the error obtained without noise and with respect to the best possible error (Bayes risk). The experimental results corroborate that RMBoost is not only resilient to label noise but can also provide strong classification accuracy.