Results 101 to 110 of about 549,786 (309)

Variational Self-Supervised Learning

We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on input reconstruction via a decoder, VSSL symmetrically couples two encoders with Gaussian outputs.
Yavuz, Mehmet Can, Yanikoglu, Berrin
openaire   +2 more sources

Learning with multimodal self-supervision

, 2021
Deep learning has fueled an explosion of applications, yet training deep neural networks usually requires expensive human annotations. In this thesis we explore alternatives to avoid the substantial reliance on manual annotated examples when training deep neural networks.
openaire   +2 more sources

Mixture of Self-Supervised Learning

, 2023
Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a pretext task which will be trained on the model before being applied to a specific task. There are some examples of
Ruslim, Aristo Renaldo, Yudistira, Novanto, Setiawan, Budi Darma   +2 more
openaire   +2 more sources

Redefining Therapies for Drug‐Resistant Tuberculosis: Synergistic Effects of Antimicrobial Peptides, Nanotechnology, and Computational Design

Advanced Healthcare Materials, EarlyView.
Antimicrobial peptide (AMP)‐loaded nanocarriers provide a multifunctional strategy to combat drug‐resistant Mycobacterium tuberculosis. By enhancing intracellular delivery, bypassing efflux pumps, and disrupting bacterial membranes, this platform restores phagolysosome fusion and macrophage function.
Christian S. Carnero Canales, Jessica Ingrid Marquez Cazorla, Renzo Marianito Marquez Cazorla, Aline Martins dos Santos, Jonatas Lobato Duarte, Letícia Oliveira Catarin Nunes, Túlio Custódio Reis, Lara Cerazi Salvador, Norival Alves Santos‐Filho, Rafael Miguel Sábio, Hélder A. Santos, Fernando Rogério Pavan   +11 more
wiley   +1 more source

Self-supervised Metric Learning

, 2022
H Μάθηση Μετρικής είναι ένα σημαντικό παράδειγμα για μία πληθώρα προβλημάτων της Μηχανικής Μάθησης και της Όρασης Υπολογιστών. Έχει επιτυχημένα εφαρμοστεί σε ε- φαρμογές όπως η λεπτομερής ταξινόμηση, ανάκτηση πληροφορίας, αναγνώριση προσώ- που κ.α. Αφορά την εκμάθηση μιας μετρικής απόστασης που βασίζεται στον προσδιορι- σμό ομοιοτήτων ή ανομοιοτήτων ...
openaire   +1 more source

Self-Supervised Multimodal Learning: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Accepted to IEEE T ...
Yongshuo Zong, Oisin Mac Aodha, Timothy M. Hospedales   +2 more
openaire   +3 more sources

Hybrid Nanofibers for Multimodal Accelerated Wound Healing

Advanced Healthcare Materials, EarlyView.
Fabrication of wound healing scaffolds based on biocompatible nanofibers. Nanofibers offering high surface area, flexibility, and biocompatibility significantly improved the healing outcome in vivo. Histological, immunological, and anti‐inflammatory markers are noticeably better in treated wounds.
Viraj P. Nirwan, Bence Bajusz, Norbert Fabók, Marina Rudan Dimlic, Jelena Budimir, Tshepang Mqatywa, Miklós Gyöngy, Márton Ferencz, Dorottya Kocsis, Olexandr Bondarenko, Mariia Rolduhina, Milena Lengyel, Istvan Antal, Rebecca Hengsbach, Franciska Erdő, Amir Fahmi   +15 more
wiley   +1 more source

siRNA Delivery via Cross‐Linked Gelatin Microparticles Enables Targeted Modulation of Osteogenic‐Vascular Cross‐Talk: An Advanced Human 3D in Vitro Test System for Therapeutic siRNA

Advanced Healthcare Materials, EarlyView.
Osteogenic‐angiogenic cross‐talk is a vital prerequisite for vascularized bone regeneration. In this study, we investigated the effects of siRNA‐mediated silencing of two inhibitory proteins, Chordin and WWP‐1, via CaP‐NP‐loaded gelatin microparticles in osteogenically differentiated microtissues.
Franziska Mitrach, Jonas Kubat, Stefan Simm, Alexandra H. Springwald, Burak Demir, Anton Liebezeit, Michael C. Hacker, Michaela Schulz‐Siegmund   +7 more
wiley   +1 more source

Unsupervised end-to-end training with a self-defined target

Neuromorphic Computing and Engineering
Designing algorithms for versatile AI hardware that can learn on the edge using both labeled and unlabeled data is challenging. Deep end-to-end training methods incorporating phases of self-supervised and supervised learning are accurate and adaptable to
Dongshu Liu, Jérémie Laydevant, Adrien Pontlevy, Damien Querlioz, Julie Grollier   +4 more
doaj   +1 more source

Enhancing Self-Supervised Learning through Explainable Artificial Intelligence Mechanisms: A Computational Analysis

Big Data and Cognitive Computing
Self-supervised learning continues to drive advancements in machine learning. However, the absence of unified computational processes for benchmarking and evaluation remains a challenge.
Elie Neghawi, Yan Liu
doaj   +1 more source