Cognitive Systems Research最新文献

{"title":"Circling the void: Using Heidegger and Lacan to think about large language models","authors":"Marc Heimann,&nbsp;Anne-Friederike Hübener","doi":"10.1016/j.cogsys.2025.101349","DOIUrl":"10.1016/j.cogsys.2025.101349","url":null,"abstract":"<div><div>The essay aims to unite two currently distinct lines of thinking and working with language. Large Language Models and continental philosophy, especially Martin Heidegger’s thinking about language and, building upon Sigmund Freud, Jacques Lacan’s structural psychoanalysis. We show that the concept of language that Heidegger, Freud and Lacan discuss and utilize in clinical frameworks is matched quite strongly by modern LLMs. This allows us to discuss a problem of negation and negativity that is central to the continental discourse but missing in current LLM research. This also means that we offer a radically different approach than is usual in the philosophy of artificial intelligence, since we base our concepts on thinkers that are often disregarded in the analytic philosophy discourse that is closer linked to AI research. To this end we also highlight, where the ontological differences of the proposed approach lie. However, our aim is to address AI researcher and continental philosophers.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"91 ","pages":"Article 101349"},"PeriodicalIF":2.1,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Active exploration and working memory synaptic plasticity shapes goal-directed behavior in curiosity-driven learning","authors":"Quentin Houbre,&nbsp;Roel Pieters","doi":"10.1016/j.cogsys.2025.101339","DOIUrl":"10.1016/j.cogsys.2025.101339","url":null,"abstract":"<div><div>The autonomous discovery and learning of robotic goals is a challenging issue to address. In this work, we propose a cognitive architecture that supports the autonomous discovery and learning of goals. To do so, we draw inspiration from neuroscience by modeling several brain processes such as attention and exploration that we articulate with curiosity-based learning. Moreover, we employ variational autoencoders and create projections of the latent spaces to dynamic neural fields through linear scaling. The aim of these projections is to investigate synaptic plasticity by varying a scaling factor. We demonstrate that a low scaling factor supports a random exploration strategy that produces more diverse actions with no tolerance regarding the discovery of similar goals. On the contrary, a sufficiently large scaling factor drives the exploration toward uncertainty reduction, focusing exploration as well as generating similar actions. In our case, we postulate that synaptic plasticity in working memory can be crucial for exploration and the learning of goals.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"91 ","pages":"Article 101339"},"PeriodicalIF":2.1,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143548011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neurons as autonomous agents: A biologically inspired framework for cognitive architectures in artificial intelligence","authors":"Artur Luczak","doi":"10.1016/j.cogsys.2025.101338","DOIUrl":"10.1016/j.cogsys.2025.101338","url":null,"abstract":"<div><div>Despite impressive recent advances in artificial intelligence (AI), current deep neural networks still lack the adaptability and energy efficiency inherent to biological systems. Here we suggest that this problem may be overcome by taking inspiration from the brain where neurons operate as autonomous agents, each capable of adjusting its synaptic connections and internal states based on local information. Currently, typical artificial neurons are static nodes, which is in striking contrast to the rich, dynamic computations performed by biological neurons. In this review, we propose redesigning artificial neurons as self-regulating, agent-like units, making actions to maximize future energy/reward. Similarly, as single-celled organisms which can autonomously navigate in complex environments in search for food, neurons can also be viewed as autonomous decision-makers, seeking to maximize their own energy resources. Thus, neurons could be operating similarly like reinforcement learning (RL) agents, which make actions to obtain maximum future reward. Here first we review literature illustrating that biological neurons perform complex computations and employ local, predictive learning rules to anticipate future activity to maximize metabolic energy. Next, we provide examples of recent biologically inspired learning algorithms where artificial neurons are empowered with computational flexibility, similarly to autonomous agents. Networks with neurons using such local learning rules can in some examples outperform current AI algorithms. We also discuss how this can improve scalability of current multi-agent systems (MAS) and energy efficiency. Therefore, designing neurons as autonomous agents may provide an important step toward building human-like cognition.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101338"},"PeriodicalIF":2.1,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Human guided empathetic AI agent for mental health support leveraging reinforcement learning-enhanced retrieval-augmented generation","authors":"Gayathri Soman,&nbsp;M.V. Judy,&nbsp;Aadhil Muhammad Abou","doi":"10.1016/j.cogsys.2025.101337","DOIUrl":"10.1016/j.cogsys.2025.101337","url":null,"abstract":"<div><div>Global mental health issues is increasing due to problems such as the social stigma around treatment, a long-neglected burdens of insufficient resources, and the rising tide of mental issues. Large language models (LLMs) can accelerate the development of comprehensive, extensive solutions that support mental health. However, the LLMs’ capability to generate and comprehend human-like conversations is one of the main challenges faced by psychiatric counselling. This work proposes a mental health counselling LLM-based conversational agent that relies on the integration of Retrieval Augmented Generation (RAG) and Reinforcement learning. RAG provides the proposed LLM-based conversational agent with contextually relevant and accurate responses through useful information extracted from a curated dataset of psychological questions and answers pooled from mental health forums. Reinforcement Learning Integrated reward Model trained with Human feedback has also been used in the proposed framework to ensure contractually of the responses generated with moral and human values. By setting up a reward mechanism that considers variables like user feedback and empathetic scores of responses, the proposed Conversational Agent learns to prioritize empathetic answers and the ones that are user preferable. With the utilization of reward-based training, the agent was able to show substantial improvements in response quality. Improved emotional alignment, steady training dynamics, decreased hallucination rates with responses having less distress and increased empathy values were the significant outcomes. The proposed methodology ensures that the conversational agent remains attentive to the emotional requirements of people seeking for mental health care and provide improved relevance and accuracy in its responses.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101337"},"PeriodicalIF":2.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combination of reward-modulated spike-timing dependent plasticity and temporal difference long-term potentiation in actor–critic spiking neural network","authors":"Yunes Tihomirov ,&nbsp;Roman Rybka ,&nbsp;Alexey Serenko ,&nbsp;Alexander Sboev","doi":"10.1016/j.cogsys.2025.101334","DOIUrl":"10.1016/j.cogsys.2025.101334","url":null,"abstract":"<div><div>This paper presents a method for training spiking neural networks (SNNs) with the actor–critic architecture. The actor SNN is trained using reward-modulated spike-timing dependent plasticity (RSTDP), and the critic SNN is trained using temporal difference long-term potentiation (TD-LTP). The proposed method achieves competitive performance on the Acrobot and CartPole benchmarks. Due to RSTDP being prospectively suitable for implementation in memristors, this result is a preliminary step towards a fully-spiking actor–critic network deployable to analog neuromorphic devices.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101334"},"PeriodicalIF":2.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building a Cognitive Twin using a distributed cognitive system and an evolution strategy","authors":"Wandemberg Gibaut,&nbsp;Ricardo Gudwin","doi":"10.1016/j.cogsys.2025.101326","DOIUrl":"10.1016/j.cogsys.2025.101326","url":null,"abstract":"<div><div>This work presents a technique to build interaction-based Cognitive Twins (a computational version of an external agent) using input–output training and an Evolution Strategy on top of a framework for distributed Cognitive Architectures. Here, we show that it is possible to orchestrate many simple physical and virtual devices to achieve good approximations of a person’s interaction behavior by training the system in an end-to-end fashion and present performance metrics. The generated Cognitive Twin may later be used to automate tasks, generate more realistic human-like artificial agents or further investigate its behaviors.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101326"},"PeriodicalIF":2.1,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A study of conceptual primitive elimination: Embedding INGEST into PTRANS","authors":"Jamie C. Macbeth,&nbsp;Alexis Kilayko","doi":"10.1016/j.cogsys.2025.101325","DOIUrl":"10.1016/j.cogsys.2025.101325","url":null,"abstract":"<div><div>In cognitive systems and cognitive linguistics, primitive decomposition systems attempt to explain cognitive phenomena by breaking things down into conceptual building blocks and provide rich and flexible representations for systems. A prime example is the Schank–Minsky Conceptual Dependency Trans-frames system, which maintains a commitment to keeping the number of primitives small and allowing them to be combined in complex ways in representing meaning, knowledge, and dynamic episodic memory. Motivated by the desire to keep the set of primitives small, this paper describes an effort to eliminate the Conceptual Dependency <span>INGEST</span> primitive and reconstitute its uses through combinations of the CD <span>PTRANS</span> primitive and CD’s representations of containment. The implementation is performed in <span>Babel</span>, an automated paraphrase generation system which generates English realizations of CD structures and which has been used in multiple natural language understanding and story understanding systems. The implementation combines the discrimination nets used for selecting word senses for the <span>INGEST</span> primitive with those for the <span>PTRANS</span> primitive. Once the implementation was complete, we also ran <span>Babel</span> using the new structures to generate paraphrases of CD structures and to determine the degree of success in our primitive re-expression endeavor.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101325"},"PeriodicalIF":2.1,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cognitive modeling based on geotagged pictures of urban landscapes using mobile electroencephalogram signals and machine learning models","authors":"Farbod Farhangi ,&nbsp;Abolghasem Sadeghi-Niaraki ,&nbsp;Seyed Vahid Razavi-Termeh ,&nbsp;Farimah Farhangi ,&nbsp;Soo-Mi Choi","doi":"10.1016/j.cogsys.2025.101324","DOIUrl":"10.1016/j.cogsys.2025.101324","url":null,"abstract":"<div><div>Evaluating the impact of urban landscapes on human cognition is a hot issue in urban studies which has progressed by producing mobile electroencephalogram (EEG) devices. However, it is still challenging to investigate the effects of urban landscapes in remote places. Nowadays, geotagged pictures share much information about urban landscapes worldwide. This work aimed to model the effect of geotagged pictures of urban landscapes on two mental states of attention and meditation using mobile EEG signals with multi-layer perceptron (MLP), random forest (RF), and support vector regression algorithms. Thirty-five picture features from 350 pictures of 39 Iran cities, and EEG signals of 32 healthy adult participants trained models. Cross-validation revealed that all models performed well with slight differences and had good generalizability. Meanwhile, the most accurate results were related to the prediction of the meditation state by RF with R² coefficient of 0.895, root mean square error of 0.149, and mean absolute error of 0.114. Correspondingly, 0.792, 0.178, and 0.14 were similar values for the prediction of attention state by MLP (the least accurate predictions). The Gini index recognized color histogram and HSV (hue, saturation, value) color space as the most important features in predictions. Generally, color features were more important than entity features, confirming the high impact of colors in landscapes. Although this research has some limitations, in line with previous works, we observed that each picture affected participants’ minds differently, existing particular elements in urban landscapes gained attention and meditation levels, and pictures of green space increased attention level more than meditation. Overall, the proposed approach may help to understand how urban landscapes affect citizens’ cognition even in unnoticed and remote places. However, using more conceptual picture features in modeling can improve the findings.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101324"},"PeriodicalIF":2.1,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Complete tableau calculi for Regular MaxSAT and Regular MinSAT","authors":"Jordi Coll ,&nbsp;Chu-Min Li ,&nbsp;Felip Manyà ,&nbsp;Elifnaz Yangin","doi":"10.1016/j.cogsys.2024.101319","DOIUrl":"10.1016/j.cogsys.2024.101319","url":null,"abstract":"<div><div>The use of constraint models in symbolic AI has significantly increased during the last decades for their capability of certifying the existence of solutions as well as their optimality. In the latter case, approaches based on the Maximum and Minimum Satisfiability problems, or MaxSAT and MinSAT, have shown to provide state-of-the-art performances in solving many computationally challenging problems of social interest, including scheduling, timetabling and resource allocation. Indeed, the research on new approaches to MaxSAT and MinSAT is a trend still providing cutting-edge advances. In this work, we push in this direction by contributing new tableaux-based calculi for solving the MaxSAT and MinSAT problems of regular propositional logic, referred to as Regular MaxSAT and Regular MinSAT problems, respectively. For these problems, we consider as well the two extensions of the highest practical interest, namely the inclusion of weights to clauses, and the distinction between hard (mandatory) and soft (desirable) constraints. Hence, our methods handle any subclass of the most general variants: Weighted Partial Regular MaxSAT and Weighted Partial Regular MinSAT. We provide a detailed description of the methods and prove that the proposed calculi are sound and complete.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101319"},"PeriodicalIF":2.1,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational model for affective processing based on Cognitive Sciences: An approach using deterministic finite automata’s and temporal heterogeneity","authors":"Carlos Zárate,&nbsp;Félix Ramos,&nbsp;Alan Christian López Fraga","doi":"10.1016/j.cogsys.2025.101322","DOIUrl":"10.1016/j.cogsys.2025.101322","url":null,"abstract":"<div><div>Cognitive architectures represent an alternative in the quest to develop general purpose artificial intelligence, for which cognitive sciences are studied. In this work we will focus on modeling affective processing, an important component to enable basic emotional capabilities. This component was developed with the aim of generating affective responses in the presence of stimuli, necessary to feed a basic emotion model already proposed within our research group. For the proposal we used a layer-based model with Deterministic Finite Automata’s (DFA) to process stimuli along the time, which works as structures to store and represent stimulus–response associations. This approach provides an independent component, contrary to the proposals commonly seen in the state of the art, where this process is often embedded in the feelings and emotions calculations. This model was tested to respond to the sounds consonance, showing that is capable to provide and reinforce responses for specific stimuli features. The results obtained show that the model is capable of making associations between the encoded stimuli and the expected responses, taking advantage of the fact that it is not necessary to be trained to identify stimulus patterns but only to learn to respond to them.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101322"},"PeriodicalIF":2.1,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}