Towards interpreting recurrent neural networks through probabilistic abstraction

Towards interpreting recurrent neural networks through probabilistic abstraction

Neural networks are becoming a popular tool for solving many realworld problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex black-box models, which hinders humans from interpreting and conse...

Saved in:

書目詳細資料
Main Authors:	DONG, Guoliang, WANG, Jingyi, SUN, Jun, ZHANG, Yang, WANG, Xinyu, DAI, Ting, DONG, Jin Song, WANG, Xingen
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2020
主題:	Abstraction Interpretation Probabilistic automata Recurrent neural networks Software Engineering
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/5947 https://ink.library.smu.edu.sg/context/sis_research/article/6950/viewcontent/1909.10023.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Singapore Management University
語言:	English

相似書籍

Towards Model-checking Probabilistic Timed Automata against Probabilistic Duration Properties
由: Dang, Van Hung, et al.
出版: (2017)

Text backdoor detection using an interpretable RNN abstract model
由: FAN, Ming, et al.
出版: (2021)

Learning probabilistic models for model checking: an evolutionary approach and an empirical study
由: WANG, Jingyi, et al.
出版: (2018)

TLV: Abstraction through testing, learning, and validation
由: SUN, Jun, et al.
出版: (2015)

Temporal Spiking Recurrent Neural Network for Action Recognition
由: Wang, W., et al.
出版: (2022)

Deepcause: Verifying neural networks with abstraction refinement
由: NGUYEN HUA GIA PHUC,
出版: (2022)

Towards an effective and interpretable refinement approach for DNN verification
由: LI, Jiaying, et al.
出版: (2023)

Training issues and learning algorithms for feedforward and recurrent neural networks
由: TEOH EU JIN
出版: (2010)

ATTENTIVE RECURRENT NEURAL NETWORKS
由: LI MINGMING
出版: (2017)

Global convergence of Lotka-Volterra recurrent neural networks with delays
由: Yi, Z., et al.
出版: (2014)

Short-term residential load forecasting based on LSTM recurrent neural network
由: Kong, Weicong, et al.
出版: (2021)

Classification of freeway traffic patterns for incident detection using constructive probabilistic neural networks
由: Jin, X., et al.
出版: (2014)

Building energy consumption raw data forecasting using data cleaning and deep recurrent neural networks
由: Yang, J., et al.
出版: (2022)

Dimension reduction in recurrent networks by canonicalization
由: Grigoryeva, Lyudmila, et al.
出版: (2022)

Sag source location and type recognition via attention-based independently recurrent neural network
由: Deng, Yaping, et al.
出版: (2021)

On robustness and interpretability in convolutional neural networks
由: Weng, Pei He
出版: (2025)

Structural damage detection by integrating data fusion and probabilistic neural network
由: Jiang, S.-F., et al.
出版: (2014)

HyDRA: hypergradient data relevance analysis for interpreting deep neural networks.
由: Chen, Yuanyuan, et al.
出版: (2021)

Development and adaptation of constructive probabilistic neural network in freeway incident detection
由: Jin, X., et al.
出版: (2014)

FAULT DETECTION AND DIAGNOSIS FOR CHILLERS USING RECURRENT NEURAL NETWORKS
由: SIM SER LYN
出版: (2021)

Modeling trajectories with recurrent neural networks
由: WU, Hao, et al.
出版: (2017)

Analyzing multi-agent systems with probabilistic model checking approach
由: Song, S., et al.
出版: (2013)

Reliability assessment for distributed systems via communication abstraction and refinement
由: GUI, Lin, et al.
出版: (2015)

APPLICATIONS OF PERTURBATION ANALYSIS IN PROBABILISTIC MODEL CHECKING
由: YAMILET ROSARIO SERRANO LLERENA
出版: (2018)

Effective learning in recurrent max-min neural networks
由: Teow, L.-N., et al.
出版: (2014)

TWO ESSAYS ON INTERPRETABLE PREDICTIVE MODELS AND MULTICALIBRATED SURVIVAL ANALYSIS FOR HEALTHCARE
由: THITI SUTTAKET
出版: (2023)

Initiative for Open Abstracts (I4OA) launches to promote discovery of research
由: Duce, Helen, et al.
出版: (2020)

In the Defiles of Abstraction
由: Flores, Patrick D.
出版: (2024)

Automatically `Verifying’ discrete-time complex systems through learning, abstraction and refinement
由: WANG, Jingyi, et al.
出版: (2018)

Study on C. elegans behaviors using recurent neural network model
由: Xu, J.-X., et al.
出版: (2014)

A hybrid intelligent model based on recurrent neural networks and excitable dynamics for price prediction in deregulated electricity market
由: Sharma, V., et al.
出版: (2014)

An interpretable neural fuzzy inference system for predictions of underpricing in initial public offerings
由: Qian, Xiaolin, et al.
出版: (2018)

Neural abstractive summarization: improvements at the sequence-level
由: Ravaut, Mathieu
出版: (2024)

Recurrent neural networks: A constructive algorithm, and its properties
由: Tsoia, A.C., et al.
出版: (2014)

Recurrent neural networks: A constructive algorithm, and its properties
由: Tsoia, A.C., et al.
出版: (2014)

Permitted and forbidden sets in discrete-time linear threshold recurrent neural networks
由: Yi, Z., et al.
出版: (2014)

ACCELERATED TRAINING OF CONSTITUTIVE RELATIONS FOR HISTORY-DEPENDENT COMPOSITE MATERIALS USING RECURRENT NEURAL NETWORK WITH TRANSFER LEARNING
由: ZHANG CHEN
出版: (2023)

Exploiting an abstract-machine-based framework in the design of a Java ILP processor
由: Wang, H.C., et al.
出版: (2013)

Analyzing multi-agent systems with probabilistic model checking approach
由: SONG, Songzheng, et al.
出版: (2012)

Should we learn probabilistic models for model checking? A new approach and an empirical study
由: WANG, Jingyi, et al.
出版: (2017)