We consider the complexity of the emptiness problem for various classes of graph languages deened by eNCE (edge label neighborhood controlled embedding) graph grammars. In particular, we show that the emptiness problem is undecidable for general eNCE graph grammars, DEXPTIME-complete for connuent and boundary eNCE graph grammars, PSPACE-complete for linear eNCE graph grammars, NL-complete for d...

We introduce relational variants of neural topographic maps including the selforganizing map and neural gas, which allow clustering and visualization of data given in terms of a pairwise similarity or dissimilarity matrix. It is assumed that this matrix originates from an euclidean distance or dot product, respectively, however, the underlying embedding of points is unknown. One can equivalentl...

We present a general framework for association learning, where entities are embedded in a common latent space to express relatedness via geometry—an approach that underlies the state of the art for link prediction, relation learning, multi-label tagging, relevance retrieval and ranking. Although current approaches rely on local training methods applied to non-convex formulations, we demonstrate...

Multi-label classification has many applications in the text categorization, biology and medical diagnosis, in which multiple class labels can be assigned to each training instance simultaneously. As it is often the case that there are relationships between the labels, extracting the existing relationships between the labels and taking advantage of them during the training or prediction phases ...

Jumlah berita atau dokumen yang sangat melimpah merupakan sumber pengetahuan berharga dan dapat digunakan untuk memperoleh wawasan dalam pengambilan keputusan. Namun, pertumbuhan jumlah dengan dimensi tinggi menjadi sebuah tantangan besar, menyebabkan sulitnya informasi pada dikategorikan secara efisien cepat. Kesulitan ini semakin kompleks tidak adanya kelas label tersebut. Analisis konten dar...

We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on labeled source data and unlabeled or sparsely labeled data in the target doma...

Nanofluidic channels are unique bioanalytical tools that can separate, detect, analyze and concentrate biomolecules. Embedding electodes in such systems increases the functionality by allowing for unique flow control, label-free sensing, and concentration enhancement. In this work, we describe the fabrication process of nanofluidic channels with integrated electrodes, as well as the characteriz...

Mature maize leaf tissue (Zea mays L.) was immunolabeled using a pre-embedding protocol with specific antibodies for nitrate reductase and protein A-colloidal gold. Immunogold label was found exclusively in the cytoplasm of mesophyll cells; no reaction was detected in bundle sheath cells. Chloroplasts, which were sliced open during cryosectioning, had no labeling. Thus, it appears nitrate reduc...

G-protein coupled receptors (GPCRs) play a key role in physiological processes and are attractive drug targets. Their biophysical characterization is, however, highly challenging because of their innate instability outside a stabilizing membrane and the difficulty of finding a suitable expression system. We here show the cell-free expression of a GPCR, CXCR4, and its direct embedding in diblock...

We introduce relational variants of neural gas, a very efficient and powerful neural clustering algorithm, which allow a clustering and mining of data given in terms of a pairwise similarity or dissimilarity matrix. It is assumed that this matrix stems from Euclidean distance or dot product, respectively, however, the underlying embedding of points is unknown. One can equivalently formulate bat...