清华大学-脑与智能实验室清华大学-脑与智能实验室发表的相关论文
CEREBRAL CORTEX, no. 2 (2019): 517-528
An important question is raised: as the insula is not considered as a part of the central auditory nervous system, what is the functional role of the auditory field in posterior insula? The present study cannot answer this question but can provide some insights
Cited by1BibtexViews78DOI
0
0
international conference on machine learning, (2018)
Our algorithms can achieve comparable convergence speed with the exact algorithm even the neighbor sampling size D(l) = 2, so that the per-epoch cost of training Graph convolution networks is comparable with training multi-layer perceptron
Cited by164BibtexViews263
0
0
neural information processing systems, pp.4584-4594, (2018)
We present a novel method to improve the robustness of deep learning models by reliably detecting and filtering out adversarial examples, which can be implemented using standard algorithms with little extra training cost
Cited by71BibtexViews178
0
0
international conference on machine learning, (2018): 4651-4660
We propose the Spectral Stein Gradient Estimator for implicit distributions
Cited by38BibtexViews178
0
0
ICML, pp.6013-6022, (2018)
We propose Message Passing Stein variational gradient descent to solve this problem when the target distribution is compactly described via a probabilistic graphical model and the conditional independence structure can be leveraged
Cited by31BibtexViews161
0
0
ICML, (2018): 4013-4022
We theoretically show that if the input samples distribute as a Max-Mahalanobis distribution, the linear discriminant analysis classifier will have the best robustness to adversarial attacks
Cited by23BibtexViews144
0
0
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), (2018): 7978-7988
We compare with a state-of-the-art algorithm, Gibbs online expectation maximization, which outperforms a wide range of algorithms including stochastic variational inference, hybrid variational-Gibbs, and SGRLD
Cited by21BibtexViews90
0
0
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), (2018): 6069-6080
This paper introduces a flexible generative modelling framework called Graphical Generative Adversarial Networks
Cited by19BibtexViews132
0
0
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), (2018): 3212-3222
Our work provides general guidelines on how to incorporate deep generative model to statistical relational models, where the proposed inference algorithm can be applied under a broader context
Cited by7BibtexViews152
0
0
Chenggang Chen, Mingxiu Cheng,Tetsufumi Ito,Sen Song
JOURNAL OF NEUROSCIENCE, no. 13 (2018): 3318-3332
After normalizing the extrinsic inputs, we found that core inhibitory neurons received a higher proportion of inhibitory inputs from the ventral nucleus of the lateral lemniscus than excitatory neurons
Cited by6BibtexViews55DOI
0
0
Xianggen Liu,Lili Mou, Haotian Cui, Zhengdong Lu,Sen Song
IJCAI, (2018): 4237-4243
Experiments show that JUMPER achieves comparable or higher performance than baselines; that it reduces text reading by a large extent; and that it can find the key rationale if the information is local within a sentence
Cited by6BibtexViews105DOI
0
0
Yichi Zhou,Jun Zhu,Jingwei Zhuo
international conference on machine learning, (2018)
We present an efficient racing algorithm for Thompson sampling with general non-conjugate priors
Cited by3BibtexViews98
0
0
Xuesong Li,Xiaodong Ma, Lyu Li,Zhe Zhang,Xue Zhang,Yan Tong, Lihong Wang,Sen Song,Hua Guo
NeuroImage, (2018): 172-182
The reconstructed images of one frame and the corresponding error maps by different methods are shown in Fig. 4A and B, and the root-mean-square error values of all frames are plotted in Fig. 4C and D
Cited by1BibtexViews103DOI
0
0
Yue Ding, Kathleen Gray, Alexander Forrence,Xiaoqin Wang,Juan Huang
PloS one, no. 8 (2018)
Two types of tone sequences were used as testing materials: musical tone sequences and random tone sequences
Cited by0BibtexViews50DOI
0
0
Zhe Zhao, Liang Wang, Wenling Gao,Fei Hu,Juen Zhang, Yuqi Ren,Rui Lin,Qiru Feng, Mingxiu Cheng, Dapeng Ju, Qingsheng Chi, Dehua Wang
Neuron, no. 1 (2017): 138-152.e5
We found reduced between-hemisphere connectivity was related to depressive episodes, whereas reduced global or nodal clustering efficiency was correlated with cognitive dysfunction in geriatric depression
Cited by10BibtexViews64DOI
0
0
HUMAN BRAIN MAPPING, no. 1 (2017): 53-67
Following LPS challenge, Fos expression was observed within subsets of tyrosine hydroxylase-immunoreactive neurons, including those in the locus coeruleus, nucleus tractus solitaries, and ventrolateral medulla, suggesting that these groups of CA neurons are responsive to LPS stre...
Cited by4BibtexViews60DOI
0
0
小科