Brain-inspired global-local learning incorporated with neuromorphic computing

There are two principle approaches for learning in artificial intelligence: error-driven global learning and neuroscience-oriented local learning. Integrating them into one network may provide complementary learning capabilities for versatile learning scenarios. At the same time, neuromorphic computing holds great promise, but still needs plenty of useful algorithms and algorithm-hardware co-designs to fully exploit its advantages. Here, we present a neuromorphic global-local synergic learning model by introducing a brain-inspired meta-learning paradigm and a differentiable spiking model incorporating neuronal dynamics and synaptic plasticity. It can meta-learn local plasticity and receive top-down supervision information for multiscale learning. We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors. It achieves significantly higher performance than single-learning methods. We further implement the model in the Tianjic neuromorphic platform by exploiting algorithm-hardware co-designs and prove that the model can fully utilize neuromorphic many-core architecture to develop hybrid computation paradigm.

Ecosistemas locales de aprendizaje ante la globalización tecnológica. Retos de los modelos educativos digitales pospandemia

La educación frente a la covid-19 ha puesto en práctica una infinidad de respuestas, todas urgentes, tentativas, generadas por ensayo y por error, y todavía pendientes de validación. Para comprender mejor el impacto de estas respuestas, el presente artículo defiende, partiendo de la teoría de los ecosistemas de aprendizaje, la necesidad de investigar cómo han influido las tecnologías de ámbito global en la construcción de experiencias locales de aprendizaje. Además, pone de manifiesto la necesidad de estudiar qué tipo de apoyo tanto teórico como práctico se requiere para reconducir los posibles efectos nocivos de la introducción de la tecnología de emergencia. A tal efecto, se describen las consecuencias de fenómenos globalizadores, como el tecnocentrismo, el solucionismo tecnológico, la plataformización y la economía de datos, proponiendo la reflexión, la concienciación para la transformación y la acción desde los ecosistemas locales de aprendizajes como vía imprescindible para la conceptualización de nuevos modelos educativos digitales pospandemia. El artículo también resume las aportaciones principales de los otros trabajos que forman parte de la monografía. Education has offered multiple, urgent, and tentative responses to Covid-19, generated by trial and error and still pending validation. To understand the impact of these responses, this article advocates for the study of how global technologies have influenced the pursuit of local learning experiences. In addition, the article emphasizes the need to investigate what kinds of theoretical and practical support are required to counterbalance the possible negative effects of emergency technology responses. Accordingly, it describes the consequences of globalizing phenomena, such as technocentrism, technological solutionism, platformization and data economy, and suggests that the reflection, critical consciousness engaged in transformation and action from within each local learning ecosystem are necessary to conceptualize new post-pandemic educational digital models. The article also summarizes the main contributions of the works included in this special issue.

Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction

Background: Machine learning models have been developed for numerous medical prognostic purposes. These models are commonly developed using data from single centers or regional registries. Including data from multiple centers improves robustness and accuracy of prognostic models. However, data sharing between multiple centers is complex, mainly because of regulations and patient privacy issues.Objective: We aim to overcome data sharing impediments by using distributed ML and local learning followed by model integration. We applied these techniques to develop 1-year TAVI mortality estimation models with data from two centers without sharing any data.Methods: A distributed ML technique and local learning followed by model integration was used to develop models to predict 1-year mortality after TAVI. We included two populations with 1,160 (Center A) and 631 (Center B) patients. Five traditional ML algorithms were implemented. The results were compared to models created individually on each center.Results: The combined learning techniques outperformed the mono-center models. For center A, the combined local XGBoost achieved an AUC of 0.67 (compared to a mono-center AUC of 0.65) and, for center B, a distributed neural network achieved an AUC of 0.68 (compared to a mono-center AUC of 0.64).Conclusion: This study shows that distributed ML and combined local models techniques, can overcome data sharing limitations and result in more accurate models for TAVI mortality estimation. We have shown improved prognostic accuracy for both centers and can also be used as an alternative to overcome the problem of limited amounts of data when creating prognostic models.

Design of an Interactive Web Application for Teaching Uncertainty Interpretations of Clinical Tests

Background: Assessing the uncertainty of diagnostic findings is essential for advising patients. Previous research has demonstrated the difficulty of computing the expected correctness of positive or negative results, although clinical decision support (CDS) tools promise to facilitate adequate interpretations. Objectives: To teach the potential utility of CDS tools to medical students, we designed an interactive software module that computes and visualizes relevant probabilities from typical inputs. Methods: We reviewed the literature on recommended graphical approaches and decided to support contingency tables, plain table formats, tree diagrams, and icon arrays. Results: We implemented these functions in a single-page web application, which was configured to complement our local learning management system where students also access interpretation tasks. Conclusion: Our technical choices promoted a rapid implementation. We intend to explore the utility of the tool during some upcoming courses. Future developments could also model a more complex clinical reality where the likelihood of alternative diagnoses is estimated from sets of clinical investigations.

Recipe for a Good Life

Recipe for a Good Life (2019) was an art exhibition at the Brindley in Cheshire which explored what it means to live a “good life” to local learning disabled people. Curated by self-advocate Leah Jones, it featured artworks created via a public participatory arts programme, where self-advocates, SEND schools, disability professionals, families, carers, and gallery visitors came together to share their different visions of what living a good life meant to them. This article documents and reflects on this exhibition using a life story approach. By describing the exhibition from Leah’s own perspective, this article offers an account of how this exhibition was curated, and furthermore, how her curatorial work and life as a self-advocate intersect, demonstrating the important role people with learning disabilities have the potential to play in culture as artists, communicators, and curators.