Asieh Abolpour Mofrad

Simulations offer a valuable tool for exploring stimulus equivalence (SE), yet the potential of reject relations to disrupt the assessment of equivalence class formation is contentious. This study investigates the role of reject relations in the acquisition of stimulus equivalence using computational models. We examined feedforward neural networks (FFNs), bidirectional encoder representations from transformers (BERT), and generative pre-trained transformers (GPT) across 18 conditions in matching-to-sample (MTS) simulations. Conditions varied in training structure (linear series, one-to-many, and many-to-one), relation type (select-only, reject-only, and select-reject), and negative comparison selection (standard and biased). A probabilistic agent served as a benchmark, embodying purely associative learning. The primary goal was to determine whether artificial neural networks could demonstrate equivalence class formation or whether their performance reflected associative learning. Results showed that reject relations influenced agent performance. While some agents achieved high accuracy on equivalence tests, particularly with reject relations and biased negative comparisons, this performance was comparable to the probabilistic agent. These findings suggest that artificial neural networks, including transformer models, may rely on associative strategies rather than SE. This underscores the need for careful consideration of reject relations and more stringent criteria in computational models of equivalence.

Background and objectives: The incidence rate of Parkinson’s disease (PD) has been increasing rapidly during the last years. Yet, no treatments exist to prevent or slow the progression of the disease. Moreover, we are unable to detect early disease stages during which intervention with disease-modifying therapies is most likely to succeed. The objective of this study was to perform an agnostic drug-wide association study (DWAS) estimating the association between use of any of the drugs prescribed in Norway and the subsequent risk of PD. Methods: This registry-based cohort study use data from the entire Norwegian population between 2004–2019 linked to the Norwegian Prescription Registry, with more than 600 million individual prescriptions. Drug classes were screened according to ATC codes at level 2, corresponding to therapeutic subgroups. We used Cox regression models to estimate hazard ratios (HRs) and 95% confidence intervals (95% CI) for the associations between drug classes and PD risk. All p-values were corrected for multiple testing using the false discovery rate. Additionally, we conducted sensitivity analyses of exposure definition, as well as time-lag and dose-response analyses. Results: The study population comprised 3,223,672 individuals, 15,849 of whom developed PD during the follow-up. We identified thirty-one drug classes that were statistically significantly associated with PD risk in Norway during the follow-up. Drugs acting on the renin-angiotensin system (HR = 0.92, 95% CI: 0.89–0.95), corticosteroids for systemic use (0.88, 95% CI: 0.84–0.93), and vaccines (0.89, 95% CI: 0.82–0.96) were associated with a decreased risk of PD even up to 10 years prior to PD onset. Drug classes used to treat symptoms related to prodromal signs of PD such as constipation, urological issues, and depression were associated with an increased risk of subsequent diagnosis of PD with HRs of 1.6 (95% CI: 1.49–1.73), 1.48 (1.42–1.53), and 1.94 (1.87–2.01), respectively. Discussion: This drug-wide study identified thirty-one drug classes that were associated with the PD risk change. It reveals links of renin-angiotensin system medications, vaccines, and corticosteroids with PD risk and suggests that monitoring drug usage using pharmacoepidemiology may allow identifying individuals with prodromal PD.

Associative memories enjoy many interesting properties in terms of error correction capabilities, robustness to noise, storage capacity, and retrieval performance, and their usage spans over a large set of applications. In this letter, we investigate and extend tournament-based neural networks, originally proposed by Jiang, Gripon, Berrou, and Rabbat (2016), a novel sequence storage associative memory architecture with high memory efficiency and accurate sequence retrieval. We propose a more general method for learning the sequences, which we call feedback tournament-based neural networks. The retrieval process is also extended to both directions: forward and backward—in other words, any large-enough segment of a sequence can produce the whole sequence. Furthermore, two retrieval algorithms, cache-winner and explore-winner, are introduced to increase the retrieval performance. Through simulation results, we shed light on the strengths and weaknesses of each algorithm.

Formation of stimulus equivalence classes has been recently modeled through equivalence projective simulation (EPS), a modified version of a projective simulation (PS) learning agent. PS is endowed with an episodic memory that resembles the internal representation in the brain and the concept of cognitive maps. PS flexibility and interpretability enable the EPS model and, consequently the model we explore in this letter, to simulate a broad range of behaviors in matching-to-sample experiments. The episodic memory, the basis for agent decision making, is formed during the training phase. Derived relations in the EPS model that are not trained directly but can be established via the network's connections are computed on demand during the test phase trials by likelihood reasoning. In this letter, we investigate the formation of derived relations in the EPS model using network enhancement (NE), an iterative diffusion process, that yields an offline approach to the agent decision making at the testing phase. The NE process is applied after the training phase to denoise the memory network so that derived relations are formed in the memory network and retrieved during the testing phase. During the NE phase, indirect relations are enhanced, and the structure of episodic memory changes. This approach can also be interpreted as the agent's replay after the training phase, which is in line with recent findings in behavioral and neuroscience studies. In comparison with EPS, our model is able to model the formation of derived relations and other features such as the nodal effect in a more intrinsic manner. Decision making in the test phase is not an ad hoc computational method, but rather a retrieval and update process of the cached relations from the memory network based on the test trial. In order to study the role of parameters on agent performance, the proposed model is simulated and the results discussed through various experimental settings.

An adaptive task difficulty assignment method which we reckon as balanced difficulty task finder (BDTF) is proposed in this paper. The aim is to recommend tasks to a learner using a trade-off between skills of the learner and difficulty of the tasks such that the learner experiences a state offlowduring the learning. Flow is a mental state that psychologists refer to when someone is completely immersed in an activity. Flow state is a multidisciplinary field of research and has been studied not only in psychology, but also neuroscience, education, sport, and games. The idea behind this paper is to try to achieve a flow state in a similar way as Elo’s chess skill rating (Glickman in Am Chess J 3:59–102) and TrueSkill (Herbrich et al. in Advances in neural information processing systems, 2006) for matching game players, where “matched players” should possess similar capabilities and skills in order to maintain the level of motivation and involvement in the game. The BDTF draws analogy between choosing an appropriate opponent or appropriate game level and automatically choosing an appropriate difficulty level of a learning task. This method, as an intelligent tutoring system, could be used in a wide range of applications from online learning environments and e-learning, to learning and remembering techniques in traditional methods such as adjusting delayed matching to sample and spaced retrieval training that can be used for people with memory problems such as people with dementia.

Stimulus equivalence (SE) and projective simulation (PS) study complex behavior, the former in human subjects and the latter in artificial agents. We apply the PS learning framework for modeling the formation of equivalence classes. For this purpose, we first modify the PS model to accommodate imitating the emergence of equivalence relations. Later, we formulate the SE formation through the matching-to-sample (MTS) procedure. The proposed version of PS model, called the equivalence projective simulation (EPS) model, is able to act within a varying action set and derive new relations without receiving feedback from the environment. To the best of our knowledge, it is the first time that the field of equivalence theory in behavior analysis has been linked to an artificial agent in a machine learning context. This model has many advantages over existing neural network models. Briefly, our EPS model is not a black box model, but rather a model with the capability of easy interpretation and flexibility for further modifications. To validate the model, some experimental results performed by prominent behavior analysts are simulated. The results confirm that the EPS model is able to reliably simulate and replicate the same behavior as real experiments in various settings, including formation of equivalence relations in typical participants, nonformation of equivalence relations in language-disabled children, and nodal effect in a linear series with nodal distance five. Moreover, through a hypothetical experiment, we discuss the possibility of applying EPS in further equivalence theory research.

Clique-based neural associative memories introduced by Gripon and Berrou (GB), have been shown to have good performance, and in our previous work we improved the learning capacity and retrieval rate by local coding and precoding in the presence of partial erasures. We now take a step forward and consider nested-clique graph structures for the network. The GB model stores patterns as small cliques, and we here replace these by nested cliques. Simulation results show that the nested-clique structure enhances the clique-based model.

Techniques from coding theory are able to improve the efficiency of neuroinspired and neural associative memories by forcing some construction and constraints on the network. In this letter, the approach is to embed coding techniques into neural associative memory in order to increase their performance in the presence of partial erasures. The motivation comes from recent work by Gripon, Berrou, and coauthors, which revisited Willshaw networks and presented a neural network with interacting neurons that partitioned into clusters. The model introduced stores patterns as small-size cliques that can be retrieved in spite of partial error. We focus on improving the success of retrieval by applying two techniques: doing a local coding in each cluster and then applying a precoding step. We use a slightly different decoding scheme, which is appropriate for partial erasures and converges faster. Although the ideas of local coding and precoding are not new, the way we apply them is different. Simulations show an in...