Abstract null null Multi-view clustering has become an active topic in artificial intelligence. Yet, similar investigation for graph-structured data clustering has been absent so far. To fill this gap, we present a Multi-View Graph embedding Clustering network (MVGC). Specifically, unlike traditional multi-view construction methods, which are only suitable to describe Euclidean structure data, we leverage Euler transform to augment the node attribute, as a new view descriptor, for non-Euclidean ...
Last. Morten Brun(University of Bergen)H-Index: 10
view all 4 authors...
Abstract null null The Delta method is a classical procedure for quantifying epistemic uncertainty in statistical models, but its direct application to deep neural networks is prevented by the large number of parameters null null null P null null . We propose a low cost approximation of the Delta method applicable to null null null null null L null null null 2 null null null null -regularized deep neural networks based on the top null null null K null null null eigenpairs of the Fisher informati...
Abstract null null The intersection between neuroscience and artificial intelligence (AI) research has created synergistic effects in both fields. While neuroscientific discoveries have inspired the development of AI architectures, new ideas and algorithms from AI research have produced new ways to study brain mechanisms. A well-known example is the case of reinforcement learning (RL), which has stimulated neuroscience research on how animals learn to adjust their behavior to maximize reward. In...
#1Shuokai Li(CAS: Chinese Academy of Sciences)H-Index: 2
#2Xiang Ao(CAS: Chinese Academy of Sciences)H-Index: 14
Last. Qing He(CAS: Chinese Academy of Sciences)H-Index: 36
view all 4 authors...
When training deep learning models, data augmentation is an important technique to improve the performance and alleviate overfitting. In natural language processing (NLP), existing augmentation methods often use fixed strategies. However, it might be preferred to use different augmentation policies in different stage of training, and different datasets may require different augmentation policies. In this paper, we take dynamic policy scheduling into consideration. We design a search space over a...
Last. Jie Tan(CAS: Chinese Academy of Sciences)H-Index: 10
view all 5 authors...
In unsupervised domain adaptation (UDA), many efforts are taken to pull the source domain and the target domain closer by adversarial training. Most methods focus on aligning distributions or features between the source domain and the target domain. However, little attention is paid to the interaction between finer-grained levels, such as classes or samples of the two domains. In contrast to UDA, another transfer learning task, i.e., few-shot learning (FSL), takes full advantage of the finer-gra...
Last. Yuichi Iino(UTokyo: University of Tokyo)H-Index: 35
view all 6 authors...
Abstract null null It is one of the ultimate goals of ethology to understand the generative process of animal behavior, and the ability to reproduce and control behavior is an important step in this field. However, it is not easy to achieve this goal in systems with complex and stochastic dynamics such as animal behavior. In this study, we have shown that MDN–RNN,a type of probabilistic deep generative model, is able to reproduce stochastic animal behavior with high accuracy by modeling the beha...
#2J. Wang(CityU: City University of Hong Kong)H-Index: 94
Abstract null null Portfolio optimization is one of the most important investment strategies in financial markets. It is practically desirable for investors, especially high-frequency traders, to consider cardinality constraints in portfolio selection, to avoid odd lots and excessive costs such as transaction fees. In this paper, a collaborative neurodynamic optimization approach is presented for cardinality-constrained portfolio selection. The expected return and investment risk in the Markowit...
Integrating multi-scale predictions has become a mainstream paradigm in edge detection. However, most existing methods mainly focus on effective feature extraction and multi-scale feature fusion while ignoring the low learning capacity in fine-level branches, limiting the overall fusion performance. In light of this, we propose a novel Fine-scale Corrective Learning Net (FCL-Net) that exploits semantic information from deep layers to facilitate fine-scale feature learning. FCL-Net mainly consist...
Abstract null null Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there is still a lack of control over the generation process in order to achieve semantic face editing. In this paper, we propose a novel learning framework, called GuidedStyle, to achieve semantic face editing on pretrained StyleGAN by guiding the image generation process with a knowledge network. Furthermore, we ...
Last. Pascual Campoy(UPM: Technical University of Madrid)H-Index: 32
view all 4 authors...
Abstract null null Counting objects in images is a very time-consuming task for humans that yields to errors caused by repetitiveness and boredom. In this paper, we present a novel object counting method that, unlike most of the recent works that focus on the regression of a density map, performs the counting procedure by localizing each single object. This key difference allows us to provide not only an accurate count but the position of every counted object, information that can be critical in...
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies. To learn more, you can find in our Privacy Policy.