The current conditions of the pandemic, as a result of Covid-19, have led university teachers to look for ways to improve the learning process and the generation of knowledge, taking advantage of the use of information technologies. This research paper proposes a model to support the learning process and knowledge generation using collaborative tools considering two aspects of importance: the management of the learning activity and the implementation using specifically the collaborative wall Padlet to facilitate student participation, team collaboration and the corresponding feedback, reinforcing the generation of knowledge. The results obtained are quite encouraging, identifying based on a satisfaction survey that students build their knowledge based on collaborative learning.

Neural networks have become a fundamental tool for solving complex problems, from image processing and speech recognition to time series prediction and large-scale data classification. However, traditional neural architectures suffer from interpretability problems due to their opaque representations and lack of explicit interaction between linear and nonlinear transformations. To address these limitations, Kolmogorov–Arnold Networks (KAN) have emerged as a mathematically grounded approach capable of efficiently representing complex nonlinear functions. Based on the principles established by Kolmogorov and Arnold, KAN offer an alternative to traditional architectures, mitigating issues such as overfitting and lack of interpretability. Despite their solid theoretical basis, practical implementations of KAN face challenges, such as optimal function selection and computational efficiency. ...