Implementation of Emotional Learning for Cognitive Tutoring Agents

Faghihi, Usef; Poirier, Pierre; Dubois, Daniel M.; Gaha, Mohamed; Nkambou, Roger

doi:10.1109/micai.2008.45

Cited by 3 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EM: When CELTS' BN starts a deliberation, for instance to build a plan, the plan is emotionally evaluated 4 The short route is a percept-reaction direct process, which takes place when the information received by the perceptual mechanism is strongly evaluated by the pseudo-amygdala. The short route is described elsewhere see [3,4]. The long route is CELTS' full cognitive cycle.…”

Section: : the Percept Enters Working Memory (Wm): The Percept Is Brmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Causes Helps a Tutoring System to Better Adapt to Learners during Training Sessions

Faghihi¹,

Fournier‐Viger²,

Nkambou³

et al. 2011

JILSA

Self Cite

View full text Add to dashboard Cite

This paper describes a computational model for the implementation of causal learning in cognitive agents. The Conscious Emotional Learning Tutoring System (CELTS) is able to provide dynamic fine-tuned assistance to users. The integration of a Causal Learning mechanism within CELTS allows CELTS to first establish, through a mix of datamining algorithms, gross user group models. CELTS then uses these models to find the cause of users' mistakes, evaluate their performance, predict their future behavior, and, through a pedagogical knowledge mechanism, decide which tutoring intervention fits best.

show abstract

Section: : the Percept Enters Working Memory (Wm): The Percept Is Brmentioning

confidence: 99%

“…One of CELTS' most significant limitations in its current implementation is its incapacity to find out why a learner made a mistake-the causes of the mistake. To address this issue, we propose to implement a Causal Learning mechanism (CLM) in CELTS and combine it with its existing Emotional Learning mechanism (see [3,4] for more details).…”

Section: Introductionmentioning

confidence: 99%

Identifying Causes Helps a Tutoring System to Better Adapt to Learners during Training Sessions

Faghihi¹,

Fournier‐Viger²,

Nkambou³

et al. 2011

JILSA

Self Cite

View full text Add to dashboard Cite

show abstract

“…In CTS, a "pseudo-amygdala" is responsible for emotional reactions [6]. In this work, we have added also a pseudohippocampus (PH) which mediates all declarative memory in CTS [5].…”

Section: Episodic Memory In Cts Architecturementioning

confidence: 99%

“…This as well as the information learned by CTS's Learning Mechanisms (i.e. learning of regularities, procedural learning and emotional learning during arm manipulation) [6] is distributed and then integrated in the same database separately from Episodic Memory. With this method, CTS clearly relates an episode to its corresponding procedures in the BN.…”

Section: Episodic and Procedural Learning In Ctsmentioning

confidence: 99%

“…These intervene in the memorization and the retrieval phases of the events in CTS's memory architecture respectively. The memorization phase of the CTS architecture includes emotional valences ascribed to ongoing events by the Emotional Mechanism [6]. Emotional valences are here taken to be CTS's memorization of valenced reactions to given emotional situations (stimuli) as described in the OCC model [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

How emotional mechanism helps episodic learning in a cognitive agent

Faghihi

Fournier‐Viger

Nkambou

et al. 2009

2009 IEEE Symposium on Intelligent Agents

Self Cite

View full text Add to dashboard Cite

In this paper we propose the CTS (Concious Tutoring System) technology, a biologically plausible cognitive agent based on human brain functions.This agent is capable of learning and remembering events and any related information such as corresponding procedures, stimuli and their emotional valences. Our proposed episodic memory and episodic learning mechanism are closer to the current multiple-trace theory in neuroscience, because they are inspired by it [5] contrary to other mechanisms that are incorporated in cognitive agents. This is because in our model emotions play a role in the encoding and remembering of events. This allows the agent to improve its behavior by remembering previously selected behaviors which are influenced by its emotional mechanism. Moreover, the architecture incorporates a realistic memory consolidation process based on a data mining algorithm.

show abstract