Related papers: Iterative collaborative routing among equivariant …
Partial differential equation (PDE) models and their associated variational energy formulations are often rotationally invariant by design. This ensures that a rotation of the input results in a corresponding rotation of the output, which…
Magnetic Resonance Imaging (MRI) is a widely utilized diagnostic tool in clinical settings, but its application is limited by the relatively long acquisition time. As a result, fast MRI reconstruction has become a significant area of…
Modern machine learning models excel at pattern recognition but remain brittle, often failing to generalize out of distribution (OOD) because they capture spurious correlations rather than the underlying causal data-generating process.…
Network robustness is critical for various societal and industrial networks again malicious attacks. In particular, connectivity robustness and controllability robustness reflect how well a networked system can maintain its connectedness…
Unsupervised learning of compact and relevant state representations has been proved very useful at solving complex reinforcement learning tasks. In this paper, we propose a recurrent capsule network that learns such representations by…
This paper presents a new concept formation approach that supports the ability to incrementally learn and predict labels for visual images. This work integrates the idea of convolutional image processing, from computer vision research, with…
Constructing model-agnostic group equivariant networks, such as equitune (Basu et al., 2023b) and its generalizations (Kim et al., 2023), can be computationally expensive for large product groups. We address this problem by providing…
Emerging applications such as networked robotics, intelligent transportation, smart factories, and virtual and augmented reality demand integrated perception and connectivity enabled by wireless communication. This has driven growing…
Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, while sensor rotations collapse activity recognition…
Multi-modal learning focuses on training models by equally combining multiple input data modalities during the prediction process. However, this equal combination can be detrimental to the prediction accuracy because different modalities…
The sample-based Gibbs sampler has been the dominant method for approximating joint distribution from a collection of compatible full-conditional distributions. However for conditionally specified model, mixtures of incompatible full and…
Although well-trained deep neural networks have shown remarkable performance on numerous tasks, they rapidly forget what they have learned as soon as they begin to learn with additional data with the previous data stop being provided. In…
Monolithic neural networks that make use of a single set of weights to learn useful representations for downstream tasks explicitly dismiss the compositional nature of data generation processes. This characteristic exists in data where…
Collaborative learning has successfully applied knowledge transfer to guide a pool of small student networks towards robust local minima. However, previous approaches typically struggle with drastically aggravated student homogenization…
Effective feature fusion of multispectral images plays a crucial role in multi-spectral object detection. Previous studies have demonstrated the effectiveness of feature fusion using convolutional neural networks, but these methods are…
Inspired by the concept of network algebraic connectivity, we adopt an extended notion named rigidity preservation index to characterize the rigidity property for a formation framework. A gradient based controller is proposed to ensure the…
Rotation invariance has been studied in the computer vision community primarily in the context of small in-plane rotations. This is usually achieved by building invariant image features. However, the problem of achieving invariance for…
Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the…
To date, most probabilistic reasoning systems have relied on a fixed belief network constructed at design time. The network is used by an application program as a representation of (in)dependencies in the domain. Probabilistic inference…
I/Q modulation classification is a unique pattern recognition problem as the data for each class varies in quality, quantified by signal to noise ratio (SNR), and has structure in the complex-plane. Previous work shows treating these…