that if extrapolation is possible, the mechanics involve developing a linkage between the extrapolating object and the extrapolating agent.; In this thesis project we focus on an investigation of a mathematical approach to extrapolation, using a combination of a modified neural network architecture and...
The modular system is based on a set of engineered bacteria that are modeled as an 'artificial neurosynapse' that, in a coculture, formed a single-layer artificial neural network-type architecture that can perform computational tasks. As a demonstration, we constructed devices that function as a...
During the past one and a half years there have been many changes to the architecture of the core algorithm. Most notably the introduction of binding-signals as the underlying mechanism for the linking process and the introduction of updatable fields which allow for a more descriptive way to imp...
In this study, we developed a multimodal deep neural network architecture, C.Origami, that incorporates both DNA sequence and genomic features for de novo prediction of cell-type-specific genome organization (Fig. 1). We found that DNA sequence information together with CTCF-binding and ATAC–seq...
Automatic cell type annotation methods are increasingly used in single-cell RNA sequencing (scRNA-seq) analysis due to their fast and precise advantages. However, current methods often fail to account for the imbalance of scRNA-seq datasets and ignore in
Intel Tensorflow or Intel Tensorflow Extension (ITEX) or Intel Extension for Tensorflow is a Tensorflow library that takes full advantage of Intel® architecture to extract maximum performance. The Tensorflow framework has been optimized using oneAPI Deep Neural Network Libr...
In this study, the revised group method of data handling (GMDH)-type neural network (NN) algorithm self-selecting the optimum neural network architecture is applied to the identification of a nonlinear system. In this algorithm, the optimum neural network architecture is automatically organized using...
HASCAD is a cell composition deconvolution (CCD) method we designed to predict the immune cell fractions in bulk RNA-seq samples. HASCAD has been implemented by using a deep neural network architecture, and it has been trained by using the reference cell-specific gene expression signatures derive...
2B). This heightened performance is a testament to the effectiveness of the feed-forward neural network architecture employed in MAPS. This architecture enables the efficient processing of spatial proteomics data, allowing for the capture of intricate relationships between input features and cell types....
Performance of the hybrid meta model In view of the diversity of the same feature extraction method for different classifiers in Sect. "Architecture of the proposed ICNN", the meta feature adds different classifier outputs. Therefore, the feature dimensions were increased from 64-D to 328-D, an...