AIMC Topic: Neural Networks, Computer

Clear Filters Showing 26731 to 26740 of 31376 articles

Zero-shot 3D anomaly detection via online voter mechanism.

Neural networks : the official journal of the International Neural Network Society
3D anomaly detection aims to solve the problem that image anomaly detection is greatly affected by lighting conditions. As commercial confidentiality and personal privacy become increasingly paramount, access to training samples is often restricted. ...

Enabling scale and rotation invariance in convolutional neural networks with retina like transformation.

Neural networks : the official journal of the International Neural Network Society
Traditional convolutional neural networks (CNNs) struggle with scale and rotation transformations, resulting in reduced performance on transformed images. Previous research focused on designing specific CNN modules to extract transformation-invariant...

A novel self-supervised graph clustering method with reliable semi-supervision.

Neural networks : the official journal of the International Neural Network Society
Cluster analysis, as a core technique in unsupervised learning, has widespread applications. With the increasing complexity of data, deep clustering, which integrates the advantages of deep learning and traditional clustering algorithms, demonstrates...

Arch-Net: Model conversion and quantization for architecture agnostic model deployment.

Neural networks : the official journal of the International Neural Network Society
The significant computational demands of Deep Neural Networks (DNNs) present a major challenge for their practical application. Recently, many Application-Specific Integrated Circuit (ASIC) chips have incorporated dedicated hardware support for neura...

Decomposition-based multi-scale transformer framework for time series anomaly detection.

Neural networks : the official journal of the International Neural Network Society
Time series anomaly detection is crucial for maintaining stable systems. Existing methods face two main challenges. First, it is difficult to directly model the dependencies of diverse and complex patterns within the sequences. Second, many methods t...

Contrastive graph auto-encoder for graph embedding.

Neural networks : the official journal of the International Neural Network Society
Graph embedding aims to embed the information of graph data into low-dimensional representation space. Prior methods generally suffer from an imbalance of preserving structural information and node features due to their pre-defined inductive biases, ...

Feature-Tuning Hierarchical Transformer via token communication and sample aggregation constraint for object re-identification.

Neural networks : the official journal of the International Neural Network Society
Recently, transformer-based methods have shown remarkable success in object re-identification. However, most works directly embed off-the-shelf transformer backbones for feature extraction. These methods treat all patch tokens equally, ignoring the d...

Structural network measures reveal the emergence of heavy-tailed degree distributions in lottery ticket multilayer perceptrons.

Neural networks : the official journal of the International Neural Network Society
Artificial neural networks (ANNs) were originally modeled after their biological counterparts, but have since conceptually diverged in many ways. The resulting network architectures are not well understood, and furthermore, we lack the quantitative t...

Event-based distributed cooperative neural learning control for nonlinear multiagent systems with time-varying output constraints.

Neural networks : the official journal of the International Neural Network Society
In practical engineering, many systems are required to operate under different constraint conditions due to considerations of system security. Violating these constraints conditions during operation may lead to performance degradation. Additionally, ...

A shape composition method for named entity recognition.

Neural networks : the official journal of the International Neural Network Society
Large language models (LLMs) roughly encode a sentence into a dense representation (a vector), which mixes up the semantic expression of all named entities within a sentence. So the decoding process is easily overwhelmed by sentence-specific informat...