A Novel Similarity Based Unsupervised Technique for Training Convolutional Filters
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3277253
Abstract: Achieving satisfactory results with Convolutional Neural Networks (CNNs) depends on how effectively the filters are trained. Conventionally, an appropriate number of filters is carefully selected, the filters are initialized with a proper initialization method and… read more here.
Keywords: based unsupervised; similarity based; novel similarity; convolutional filters ... See more keywords