Search Results for author: Shengjie Wang

Found 17 papers, 4 papers with code

Time-Consistent Self-Supervision for Semi-Supervised Learning

no code implementations ICML 2020 Tianyi Zhou, Shengjie Wang, Jeff Bilmes

In this paper, we study the dynamics of neural net outputs in SSL and show that selecting and using first the unlabeled samples with more consistent outputs over the course of training (i. e., "time-consistency") can improve the final test accuracy and save computation.

Reinforcement Learning with Prior Policy Guidance for Motion Planning of Dual-Arm Free-Floating Space Robot

1 code implementation3 Sep 2022 Yuxue Cao, Shengjie Wang, Xiang Zheng, Wenke Ma, Xinru Xie, Lei Liu

However, due to the increase in planning dimension and the intensification of system dynamics coupling, the motion planning of dual-arm free-floating space robots remains an open challenge.

Motion Planning

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

1 code implementation17 Jun 2022 Yuanpei Chen, Yaodong Yang, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Hao Dong, Zongqing Lu, Song-Chun Zhu

In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects.

Few-Shot Learning Offline RL +1

Exploring the representativeness of the M5 competition data

no code implementations4 Mar 2021 Evangelos Theodorou, Shengjie Wang, Yanfei Kang, Evangelos Spiliotis, Spyros Makridakis, Vassilios Assimakopoulos

The main objective of the M5 competition, which focused on forecasting the hierarchical unit sales of Walmart, was to evaluate the accuracy and uncertainty of forecasting methods in the field in order to identify best practices and highlight their practical implications.

Marketing Time Series

Robust Curriculum Learning: from clean label detection to noisy label self-correction

no code implementations ICLR 2021 Tianyi Zhou, Shengjie Wang, Jeff Bilmes

Neural nets training can easily overfit to noisy labels and end with poor generalization performance.

Curriculum Learning by Dynamic Instance Hardness

no code implementations NeurIPS 2020 Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes

Compared to existing CL methods: (1) DIH is more stable over time than using only instantaneous hardness, which is noisy due to stochastic training and DNN's non-smoothness; (2) DIHCL is computationally inexpensive since it uses only a byproduct of back-propagation and thus does not require extra inference.

Dynamic Instance Hardness

no code implementations25 Sep 2019 Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes

The advantages of DIHCL, compared to other curriculum learning approaches, are: (1) DIHCL does not require additional inference steps over the data not selected by DIHCL in each epoch, (2) the dynamic instance hardness, compared to static instance hardness (e. g., instantaneous loss), is more stable as it integrates information over the entire training history up to the present time.

Jumpout: Improved Dropout for Deep Neural Networks with Rectified Linear Units

no code implementations ICLR 2019 Shengjie Wang, Tianyi Zhou, Jeff Bilmes

In this paper, we discuss three novel observations about dropout to better understand the generalization of DNNs with rectified linear unit (ReLU) activations: 1) dropout is a smoothing technique that encourages each local linear model of a DNN to be trained on data points from nearby regions; 2) a constant dropout rate can result in effective neural-deactivation rates that are significantly different for layers with different fractions of activated neurons; and 3) the rescaling factor of dropout causes an inconsistency to occur between the normalization during training and testing conditions when batch normalization is also used.

Diverse Ensemble Evolution: Curriculum Data-Model Marriage

no code implementations NeurIPS 2018 Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes

We study a new method (``Diverse Ensemble Evolution (DivE$^2$)'') to train an ensemble of machine learning models that assigns data to models at each training epoch based on each model's current expertise and an intra- and inter-model diversity reward.

Mixed Robust/Average Submodular Partitioning: Fast Algorithms, Guarantees, and Applications

no code implementations NeurIPS 2015 Kai Wei, Rishabh K. Iyer, Shengjie Wang, Wenruo Bai, Jeff A. Bilmes

In the present paper, we bridge this gap, by proposing several new algorithms (including greedy, majorization-minimization, minorization-maximization, and relaxation algorithms) that not only scale to large datasets but that also achieve theoretical approximation guarantees comparable to the state-of-the-art.

Distributed Optimization Image Segmentation +2

Blending LSTMs into CNNs

no code implementations19 Nov 2015 Krzysztof J. Geras, Abdel-rahman Mohamed, Rich Caruana, Gregor Urban, Shengjie Wang, Ozlem Aslan, Matthai Philipose, Matthew Richardson, Charles Sutton

We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs.

Automatic Speech Recognition Inductive Bias +2

Mixed Robust/Average Submodular Partitioning: Fast Algorithms, Guarantees, and Applications to Parallel Machine Learning and Multi-Label Image Segmentation

no code implementations NeurIPS 2015 Kai Wei, Rishabh Iyer, Shengjie Wang, Wenruo Bai, Jeff Bilmes

While the robust versions have been studied in the theory community, existing work has focused on tight approximation guarantees, and the resultant algorithms are not, in general, scalable to very large real-world applications.

Distributed Optimization Image Segmentation +2

Faster graphical model identification of tandem mass spectra using peptide word lattices

no code implementations29 Oct 2014 Shengjie Wang, John T. Halloran, Jeff A. Bilmes, William S. Noble

Liquid chromatography coupled with tandem mass spectrometry, also known as shotgun proteomics, is a widely-used high-throughput technology for identifying proteins in complex biological samples.

Cannot find the paper you are looking for? You can Submit a new open access paper.