2018年9月1日 · We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map.

2023年9月1日 · When used in combination with the SOM, the resulting model (DASOM) is ideal for clustering high dimensional datasets with complex feature relationships [2]. Illustrating this point we used DASOM on gene expression data to separate cancer samples by cancer type.

2022年7月28日 · In authors proposed a denoising autoencoder self-organizing map (DASOM) that integrates denoising autoencoders into a hierarchically organized hybrid model. This arrangement will help learn the model parameters in an unsupervised fashion and also maintain the clustering properties.

This work is a thorough study on the deep embedded self-organizing map (DESOM), a model composed of an autoencoder and a SOM layer, training jointly the code vectors and network weights to learn...

2018年5月25日 · DASOM integrates autoencoders into a hierarchically organised hybrid model where the front-end component is a grid of topologically ordered neurons. The model maintains clustering properties but by extending and enhancing its visualisation capacity it enables an inclusion and analysis of the intermediate representative space.

We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map.

2019年3月19日 · We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end...

2018年5月24日 · DASOM integrates autoencoders into a hierarchically organised hybrid model where the front-end component is a grid of topologically ordered neurons. The model maintains clustering properties but...

We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map.

Dasom Ahn received the B.S. and M.S. degrees in computer engineering from Keimyung University, Daegu, South Korea, in 2018 and 2023, respectively, where she is currently pursuing the Ph.D. degree with the Computer Vision and Pattern Recognition Laboratory.