Zobrazeno 1 - 10
of 7 550
pro vyhledávání: '"Lee, C. S."'
Autor:
Shi, Ye, Lee, C. S. George
Irregular distribution in latent space causes posterior collapse, misalignment between posterior and prior, and ill-sampling problem in Variational Autoencoders (VAEs). In this paper, we introduce a novel adaptable three-stage Uniform Transformation
Externí odkaz:
http://arxiv.org/abs/2407.02681
Autor:
Cao, Yue, Lee, C. S. George
Layered architectures have been widely used in robot systems. The majority of them implement planning and execution functions in separate layers. However, there still lacks a straightforward way to transit high-level tasks in the planning layer to th
Externí odkaz:
http://arxiv.org/abs/2308.06810
Autor:
de Franca, F. O., Virgolin, M., Kommenda, M., Majumder, M. S., Cranmer, M., Espada, G., Ingelse, L., Fonseca, A., Landajuela, M., Petersen, B., Glatt, R., Mundhenk, N., Lee, C. S., Hochhalter, J. D., Randall, D. L., Kamienny, P., Zhang, H., Dick, G., Simon, A., Burlacu, B., Kasak, Jaan, Machado, Meera, Wilstrup, Casper, La Cava, W. G.
Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main attraction of this approach is that it returns an interpretable model that can be insightful to users. Historically, the majority of algorithms
Externí odkaz:
http://arxiv.org/abs/2304.01117
Autor:
Cao, Yue, Lee, C. S. George
Nowadays, the behavior tree is gaining popularity as a representation for robot tasks due to its modularity and reusability. Designing behavior-tree tasks manually is time-consuming for robot end-users, thus there is a need for investigating automati
Externí odkaz:
http://arxiv.org/abs/2302.12927
In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem and propose a novel multi-stage framework to solve real-world situations when the target data are unlabeled and arriving online sequentially in batches. To project the
Externí odkaz:
http://arxiv.org/abs/2207.00003
A safety-critical measure of legged locomotion performance is a robot's ability to track its desired time-varying position trajectory in an environment, which is herein termed as "global-position tracking". This paper introduces a nonlinear control a
Externí odkaz:
http://arxiv.org/abs/2108.03661
In this paper, we extend the traditional few-shot learning (FSL) problem to the situation when the source-domain data is not accessible but only high-level information in the form of class prototypes is available. This limited information setup for t
Externí odkaz:
http://arxiv.org/abs/2010.12084
Autor:
Dozono, M., Uesaka, T., Fukuda, N., Ichimura, M., Inabe, N., Kawase, S., Kisamori, K., Kiyokawa, Y., Kobayashi, K., Kobayashi, M., Kubo, T., Kubota, Y., Lee, C. S., Matsushita, M., Michimasa, S., Miya, H., Ohkura, A., Ota, S., Sagawa, H., Sakaguchi, S., Sakai, H., Sasano, M., Shimoura, S., Shindo, Y., Stuhl, L., Suzuki, H., Tabata, H., Takaki, M., Takeda, H., Tokieda, H., Wakasa, T., Yako, K., Yanagisawa, Y., Yasuda, J., Yokoyama, R., Yoshida, K., Zenihiro, J.
The parity-transfer $({}^{16}{\rm O},{}^{16}{\rm F}(0^-,{\rm g.s.}))$ reaction is presented as a new probe for investigating isovector $0^-$ states in nuclei. The properties of $0^-$ states provide a stringent test of the threshold density for pion c
Externí odkaz:
http://arxiv.org/abs/2007.15225
In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem, where the target data are unlabelled and arriving sequentially. The traditional methods on the OUDA problem mainly focus on transforming each arriving target data to
Externí odkaz:
http://arxiv.org/abs/2002.08930
Autor:
Das, Debasmit, Lee, C. S. George
This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base catego
Externí odkaz:
http://arxiv.org/abs/1912.04973