Perception Processing for General Intelligence: Bridging the Symbolic/Subsymbolic Gap

Goertzel, Ben

doi:10.1007/978-3-642-35506-6_9

Cited by 21 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is not to say that cognitive theories of reasoning predict brain activation per se, but that they predict more elementary cognitive processes that are more closely associated with activation in a particular brain region. By the identification and localization of these cognitive processes, we aim at closing the symbolic-subsymbolic gap (Goertzel, 2012) between high-level and low-level cognitive processes. We have summarized the predictions concerning brain activation for each previously described theory in Table 6.…”

Section: Discussionmentioning

confidence: 99%

The Neurocognitive Correlates of Human Reasoning: A Meta-analysis of Conditional and Syllogistic Inferences

Wertheim

Ragni

2020

Journal of Cognitive Neuroscience

View full text Add to dashboard Cite

Inferring knowledge is a core aspect of human cognition. We can form complex sentences connecting different pieces of information, such as in conditional statements like “if someone drinks alcohol, then they must be older than 18.” These are relevant for causal reasoning about our environment and allow us to think about hypothetical scenarios. Another central aspect to forming complex statements is to quantify about sets, such as in “some apples are green.” Reasoning in terms of the ability to form these statements is not yet fully understood, despite being an active field of interdisciplinary research. On a theoretical level, several conceptual frameworks have been proposed, predicting diverging brain activation patterns during the reasoning process. We present a meta-analysis comprising the results of 32 neuroimaging experiments about reasoning, which we subdivided by their structure, content, and requirement for world knowledge. In conditional tasks, we identified activation in the left middle and rostrolateral pFC and parietal regions, whereas syllogistic tasks elicit activation in Broca's complex, including the BG. Concerning the content differentiation, abstract tasks exhibit activation in the left inferior and rostrolateral pFC and inferior parietal regions, whereas content tasks are in the left superior pFC and parieto-occipital regions. The findings clarify the neurocognitive mechanisms of reasoning and exhibit clear distinctions between the task's type and content. Overall, we found that the activation differences clarify inconsistent results from accumulated data and serve as useful scaffolding differentiations for theory-driven interpretations of the neuroscientific correlates of human reasoning.

show abstract

Section: Discussionmentioning

confidence: 99%

The Neurocognitive Correlates of Human Reasoning: A Meta-analysis of Conditional and Syllogistic Inferences

Wertheim

Ragni

2020

Journal of Cognitive Neuroscience

View full text Add to dashboard Cite

show abstract

“…It is universally agreed that symbols (labels, strings of characters, frames), production rules and non-probabilistic logical inference are symbolic and distributed representations such as neural networks are sub-symbolic. For example, probabilistic action selection is considered as symbolic in CARACaS [251], CHREST [476] and CogPrime [189], but is described as subsymbolic in ACT-R [321], CELTS [151], CoJACK [434], Copycat/Metacat [350] and iCub [459]. Likewise, numeric data is treated as symbolic in CAPS [266], AIS [212] and EPIC [279], but is regarded as sub-symbolic in SASE [586].…”

Section: Taxonomies Of Cognitive Architecturesmentioning

confidence: 99%

40 years of cognitive architectures: core cognitive abilities and practical applications

2018

View full text Add to dashboard Cite

In this paper we present a broad overview of the last 40 years of research on cognitive architectures. To date, the number of existing architectures has reached several hundred, but most of the existing surveys do not reflect this growth and instead focus on a handful of well-established architectures. In this survey we aim to provide a more inclusive and highlevel overview of the research on cognitive architectures. Our final set of 84 architectures includes 49 that are still actively developed, and borrow from a diverse set of disciplines, spanning areas from psychoanalysis to neuroscience. To keep the length of this paper within reasonable limits we discuss only the core cognitive abilities, such as perception, attention mechanisms, action selection, memory, learning, reasoning and metareasoning. In order to assess the breadth of practical applications of cognitive architectures we present information on over 900 practical projects implemented using the cognitive architectures in our list. We use various visualization techniques to highlight the overall trends in the development of the field. In addition to summarizing the current state-of-the-art in the cognitive architecture research, this survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.

show abstract

“…Integrating the two approaches have also become more common to benefit of both strategies (e.g. [92,99,144]). The framework proposed in this thesis benefits of both symbolic and subsymbolic techniques.…”

Section: Introductionmentioning

confidence: 99%

Engineering Background Knowledge for Social Robots

Asprino

2020

Studies on the Semantic Web

View full text Add to dashboard Cite

Riconosco che questo questo lavoroè frutto di un percorso iniziato molti anni fa sui banchi di scuola e se oggi presento una tesi di dottorato lo devo a molte persone. Vorrei iniziare dai miei genitori perchè i loro sforzi mi hanno permesso di studiare in tutta tranquillità e perchè hanno sempre creduto in me e mi hanno incoraggiato in quello che facevo. Vorrei ringraziare le mie sorelle Rosa e Paola insieme con i loro mariti che mi hanno pazientemente sopportato durante gli anni di università. Sfrutto questa sezione per esprimere la mia riconoscenza per Fulvio, Iride, Sara ed Erminia che mi hanno accolto, ospitato, sfamato e aiutato come figlio/fratello. Vorrei inoltre dedicare questa tesi ai miei nipoti Maria Letizia, Anna Luce, Lorenzo, Vittoria e Lorena. Spero che possiate trovare anche voi un lavoro che vi appassioni e che vi renda soddisfatti giorno per giorno. Vorrei esprimere la mia più profonda gratitudine per la dr.ssa Valentina Presutti che nel 2015, credendo in me e nelle mie capacità, mi ha accettato nel suo gruppo di ricerca e in seguito mi ha guidato pazientemente per tutta la durata del dottorato. Un ringraziamento speciale lo devo al mio supervisore, prof. Paolo Ciancarini, per essere stato sempre pronto ad aiutarmi nelle mie difficoltà, per i suoi consigli e suggerimenti nelle attività di ricerca. Inoltre, vorrei ringraziare in modo particolare il prof. Aldo Gangemi per essersi sempre speso per trasferirmi le sue conoscenze allargando i miei orizzonti di ricerca. Vorrei esprimere la mia riconoscenza verso i revisori di questa tesi, la prof.ssa Eva Blomqvist e il dr. Fabien Gandon, perchè grazie ai loro commenti appassionati ho potuto migliorare questa tesi. Vorrei ringraziare il prof. vii Frank Van Harmelen e il dr. Wouter Beek perchè mi hanno calorosamente accolto e ospitato nel loro gruppo durante il mio periodo all'estero. Se sono quiè anche merito di alcuni professori che durante gli anni di università mi hanno trasmesso entusiasmo verso le materie scientifiche. Tra questi, vorrei ringraziare in modo particolare il prof. Giuseppe De Giacomo perchè la sua passione per l'intelligenza artificiale mi ha spinto verso il mondo accademico. Infine, la mia riconoscenza va a tutti i miei insegnanti e professori che si sono spesi per la mia formazione. Qui vorrei ricordarne alcuni a cui sarò sempre riconoscente: Maria Elena Coppa, prof. Vaccarone, prof.ssa Civale, prof.ssa Libertino e prof. Calabrese. Durante questi anni ho collaborato con diverse persone e anche questo lavoroè frutto del contributo di molti. In modo particolare vorrei esprimere la mia riconoscenza per Alessandro Russo e Andrea Giovanni Nuzzolese con i quali ho condiviso e continuo a condividere molte fatiche e lunghi "pellegrinaggi". Un grazie speciale va alle persone che hanno collaborato al lavoro presentato in questa tesi Mehwish

show abstract

Perception Processing for General Intelligence: Bridging the Symbolic/Subsymbolic Gap

Cited by 21 publications

References 13 publications

The Neurocognitive Correlates of Human Reasoning: A Meta-analysis of Conditional and Syllogistic Inferences

The Neurocognitive Correlates of Human Reasoning: A Meta-analysis of Conditional and Syllogistic Inferences

40 years of cognitive architectures: core cognitive abilities and practical applications

Engineering Background Knowledge for Social Robots

Contact Info

Product

Resources

About