Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1136/bmj.l2162 | DOI Listing |
Nat Commun
January 2025
Institute of Molecular Biology and Biotechnology, Foundation for Research and Technology-Hellas, Heraklion, Crete, Greece.
Artificial neural networks (ANNs) are at the core of most Deep Learning (DL) algorithms that successfully tackle complex problems like image recognition, autonomous driving, and natural language processing. However, unlike biological brains who tackle similar problems in a very efficient manner, DL algorithms require a large number of trainable parameters, making them energy-intensive and prone to overfitting. Here, we show that a new ANN architecture that incorporates the structured connectivity and restricted sampling properties of biological dendrites counteracts these limitations.
View Article and Find Full Text PDFFew-shot learning algorithms frequently exhibit suboptimal performance due to the limited availability of labeled data. This article presents a novel quantum few-shot image classification methodology aimed at enhancing the efficacy of few-shot learning algorithms at both the data and parameter levels. Initially, a quantum augmentation image representation technique is introduced, leveraging the local phase of quantum states to support few-shot learning algorithms at the data level.
View Article and Find Full Text PDFArXiv
September 2024
Institute of Molecular Biology and Biotechnology, Foundation for Research and Technology-Hellas, Heraklion, Crete 70013, Greece.
Artificial neural networks (ANNs) are at the core of most Deep learning (DL) algorithms that successfully tackle complex problems like image recognition, autonomous driving, and natural language processing. However, unlike biological brains who tackle similar problems in a very efficient manner, DL algorithms require a large number of trainable parameters, making them energy-intensive and prone to overfitting. Here, we show that a new ANN architecture that incorporates the structured connectivity and restricted sampling properties of biological dendrites counteracts these limitations.
View Article and Find Full Text PDFIEEE Trans Biomed Circuits Syst
August 2024
The spiking neural network (SNN) training with spike timing-dependent plasticity (STDP) for image classification usually requires a lot of neurons to extract representative features and(or) needs an external classifier. Conventional bio-inspired learning methods do not cover all possible learning opportunities, resulting in limited performance. We propose a new bio-plausible learning rule, target-modulated STDP (TSTDP), for higher learning efficiency and accuracy.
View Article and Find Full Text PDFPsychoneuroendocrinology
July 2024
Social Stress and Family Health Research Group, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany; Institute for Psychosocial Medicine, Psychotherapy and Psychooncology, Jena University Hospital, Friedrich-Schiller University, Jena, Germany; German Center for Mental Health (DZPG), partner site Halle-Jena-Magdeburg, Germany; Center for Intervention and Research in adaptive and maladaptive brain Circuits underlying mental health (C-I-R-C), Halle-Jena-Magdeburg, Germany.
To advance intervention science dedicated to improve refugees' mental health, a better understanding of factors of risk and resilience involved in the etiology and maintenance of post-traumatic stress disorder (PTSD) is needed. In the present study, we tested whether empathy and compassion, two trainable aspects of social cognition related to health, would modulate risk for PTSD after war-related trauma. Fifty-six refugees and 42 migrants from Arabic-speaking countries reported on their trauma experiences, PTSD symptoms, and perceived trait empathy and compassion.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!