An Improved Collaborative Filtering Recommendation Algorithm Based on Retroactive Inhibition Theory

Collaborative filtering (CF) is the most classical and widely used recommendation algorithm, which is mainly used to predict user preferences by mining the user’s historical data. CF algorithms can be divided into two main categories: user-based CF and item-based CF, which recommend items based on rating information from similar user profiles (user-based) or recommend items based on the similarity between items (item-based). However, since user’s preferences are not static, it is vital to take into account the changing preferences of users when making recommendations to achieve more accurate recommendations. In recent years, there have been studies using memory as a factor to measure changes in preference and exploring the retention of preference based on the relationship between the forgetting mechanism and time. Nevertheless, according to the theory of memory inhibition, the main factors that cause forgetting are retroactive inhibition and proactive inhibition, not mere evolutions over time. Therefore, our work proposed a method that combines the theory of retroactive inhibition and the traditional item-based CF algorithm (namely, RICF) to accurately explore the evolution of user preferences. Meanwhile, embedding training is introduced to represent the features better and alleviate the problem of data sparsity, and then the item embeddings are clustered to represent the preference points to measure the preference inhibition between different items. Moreover, we conducted experiments on real-world datasets to demonstrate the practicability of the proposed RICF. The experiments show that the RICF algorithm performs better and is more interpretable than the traditional item-based collaborative filtering algorithm, as well as the state-of-art sequential models such as LSTM and GRU.

Contextual interference effect is independent of retroactive inhibition but variable practice is not always beneficial

Positive effects of variable practice conditions on subsequent motor memory consolidation and generalization are widely accepted and described as the contextual interference effect (CIE). However, the general benefits of CIE are low and these benefits might even depend on decreased retest performances in the blocked-practicing control group, caused by retroactive inhibition. The aim of this study was to investigate if CIE represents a true learning phenomenon or possibly reflects confounding effects of retroactive inhibition. We tested 48 healthy human participants adapting their reaching movements to three different force field magnitudes. Subjects practiced the force fields in either a Blocked (B), Random (R), or Constant (C) schedule. In addition, subjects of the Blocked group performed either a retest schedule that did (Blocked-Matched; BM) or did not (Blocked-Unmatched; BU) control for retroactive inhibition. Results showed that retroactive inhibition did not affect the results of the BU group much and that the Random group showed a better consolidation performance compared to both Blocked groups. However, compared to the Constant group, the Random group showed only slight benefits in its memory consolidation of the mean performance across all force field magnitudes and no benefits in absolute performance values. This indicates that CIE reflects a true motor learning phenomenon, which is independent of retroactive inhibition. However, random practice is not always beneficial over constant practice.

Proactive inhibition and semantic organization Relationship with verbal memory in patients with schizophrenia

Compared to other cognitive functions in schizophrenia, evidence suggests that verbal memory is particularly impaired. This study used the California Verbal Learning Test (CVLT) to examine proactive inhibition (PI) and semantic processing in verbal memory in 29 patients with schizophrenia and 29 healthy controls. Patients showed significantly less PI, but also did not organize (cluster) their recall according to semantic category. Controls and patients demonstrated small retroactive inhibition (RI) effects regardless of semantic content. Although both groups made similar types and numbers of free recall intrusion errors, patients committed more phonemic and nonshared recognition errors. Results suggest that reduced semantic processing prevented build of PI, and contributes to defective memory in schizophrenia. The anatomic-physiologic abnormalities that underlie these findings may be particularly pronounced in prefrontal and temporal-parietal cortical areas. (JINS, 1996, 2, 486–493.)