Institution
Harbin Institute of Technology
Education•Harbin, China•
About: Harbin Institute of Technology is a education organization based out in Harbin, China. It is known for research contribution in the topics: Microstructure & Control theory. The organization has 88259 authors who have published 109297 publications receiving 1603393 citations. The organization is also known as: HIT.
Topics: Microstructure, Control theory, Computer science, Alloy, Laser
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this paper, a facile two-step method was adopted to develop an in-situ heterostructure with NiCo-LDH nanowire as core and NiOOH nanosheets as shell on carbon fiber cloth.
309 citations
••
TL;DR: In this paper, the resistance to electrochemical oxidation of carbon black (Vulcan XC-72) and chemical vapor deposited multiwalled carbon nanotubes (CVD-MWNTs), both widely used as catalyst supports for low temperature fuel cells, was investigated with potentiostatic oxidation in 0.5 −1 H2SO4.
308 citations
••
TL;DR: DeepGauge as discussed by the authors proposes a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed.
Abstract: Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems.
307 citations
••
TL;DR: By combining radial basis function neural networks' universal approximation ability and adaptive backstepping technique with common stochastic Lyapunov function method, an adaptive control algorithm is proposed for the considered system and it is shown that the target signal can be almost surely tracked by the system output.
307 citations
••
19 Feb 2020TL;DR: CodeBERT as mentioned in this paper is a pre-trained model for natural language code search and code documentation generation with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators.
Abstract: We present CodeBERT, a bimodal pre-trained model for programming language (PL) and natural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language code search, code documentation generation, etc. We develop CodeBERT with Transformer-based neural architecture, and train it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators. This enables us to utilize both “bimodal” data of NL-PL pairs and “unimodal data, where the former provides input tokens for model training while the latter helps to learn better generators. We evaluate CodeBERT on two NL-PL applications by fine-tuning model parameters. Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation. Furthermore, to investigate what type of knowledge is learned in CodeBERT, we construct a dataset for NL-PL probing, and evaluate in a zero-shot setting where parameters of pre-trained models are fixed. Results show that CodeBERT performs better than previous pre-trained models on NLPL probing.
307 citations
Authors
Showing all 89023 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jiaguo Yu | 178 | 730 | 113300 |
Lei Jiang | 170 | 2244 | 135205 |
Gang Chen | 167 | 3372 | 149819 |
Xiang Zhang | 154 | 1733 | 117576 |
Hui-Ming Cheng | 147 | 880 | 111921 |
Yi Yang | 143 | 2456 | 92268 |
Bruce E. Logan | 140 | 591 | 77351 |
Bin Liu | 138 | 2181 | 87085 |
Peng Shi | 137 | 1371 | 65195 |
Hui Li | 135 | 2982 | 105903 |
Lei Zhang | 135 | 2240 | 99365 |
Jie Liu | 131 | 1531 | 68891 |
Lei Zhang | 130 | 2312 | 86950 |
Zhen Li | 127 | 1712 | 71351 |
Kurunthachalam Kannan | 126 | 820 | 59886 |