Conventional supervised and unsupervised machine learning models used for landslide susceptibility prediction (LSP) have many drawbacks, such as an insufficient number of recorded landslide samples, ...and the subjective and random selection of non-landslide samples. To overcome these drawbacks, a semi-supervised multiple-layer perceptron (SSMLP) is innovatively proposed with several processes: (1) an initial landslide susceptibility map (LSM) is produced using the multiple-layer perceptron (MLP) based on the original recorded landslide samples and related environmental factors; (2) the initial LSM is respectively classified into five areas with very high, high, moderate, low and very low susceptible levels; (3) some reasonable grid units from the areas with very high susceptible level are selected as new landslide samples to expand the original landslide samples; (4) reasonable non-landslide samples are selected from the areas with very low susceptible level; and (5) the expanded landslide samples, reasonable selected non-landslide samples and related environmental factors are put into the MLP once again to predict the final LSM. The Xunwu County of Jiangxi Province in China is selected as the study area. Conventional supervised machine learning (i.e. MLP) and unsupervised machine learning (i.e. K-means clustering model) are selected for comparisons. The comparative results indicate that the SSMLP model has a considerably higher LSP performance than the MLP and K-means clustering in Xunwu County. The SSMLP model successfully addresses the drawbacks existed in the conventional machine learning for LSP.
Text classification to a hierarchical taxonomy of topics is a common and practical problem. Traditional approaches simply use bag-of-words and have achieved good results. However, when there are a ...lot of labels with different topical granularities, bag-of-words representation may not be enough. Deep learning models have been proven to be effective to automatically learn different levels of representations for image data. It is interesting to study what is the best way to represent texts. In this paper, we propose a graph-CNN based deep learning model to first convert texts to graph-of-words, and then use graph convolution operations to convolve the word graph. Graph-of-words representation of texts has the advantage of capturing non-consecutive and long-distance semantics. CNN models have the advantage of learning different level of semantics. To further leverage the hierarchy of labels, we regularize the deep architecture with the dependency among labels. Our results on both RCV1 and NYTimes datasets show that we can significantly improve large-scale hierarchical text classification over traditional hierarchical text classification and existing deep models.
Memristor-based synaptic network has been widely investigated and applied to neuromorphic computing systems for the fast computation and low design cost. As memristors continue to mature and achieve ...higher density, bit failures within crossbar arrays can become a critical issue. These can degrade the computation accuracy significantly. In this work, we propose a defect rescuing design to restore the computation accuracy. In our proposed design, significant weights in a specified network are first identified and retraining and remapping algorithms are described. For a two layer neural network with 92.64% classification accuracy on MNIST digit recognition, our evaluation based on real device testing shows that our design can recover almost its full performance when 20% random defects are present.
Lithography simulation is one of the most fundamental steps in process modeling and physical verification. Conventional simulation methods suffer from a tremendous computational cost for achieving ...high accuracy. Recently, machine learning was introduced to trade off between accuracy and runtime through speeding up the resist modeling stage of the simulation flow. In this work, we propose LithoGAN, an end-to-end lithography modeling framework based on a generative adversarial network (GAN), to map the input mask patterns directly to the output resist patterns. Our experimental results show that LithoGAN can predict resist patterns with high accuracy while achieving orders of magnitude speedup compared to conventional lithography simulation and previous machine learning based approach.
Causality-based neural network repair Sun, Bing; Sun, Jun; Pham, Long H. ...
2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE),
05/2022
Conference Proceeding
Open access
Neural networks have had discernible achievements in a wide range of applications. The wide-spread adoption also raises the concern of their dependability and reliability. Similar to traditional ...decision-making programs, neural networks can have defects that need to be repaired. The defects may cause unsafe behaviors, raise security concerns or unjust societal impacts. In this work, we address the problem of repairing a neural network for desirable properties such as fairness and the absence of backdoor. The goal is to construct a neural network that satisfies the property by (minimally) adjusting the given neural network's parameters (i.e., weights). Specifically, we propose CARE (CAusality-based REpair), a causality-based neural network repair technique that 1) performs causality-based fault localization to identify the 'guilty' neurons and 2) optimizes the parameters of the identified neurons to reduce the misbehavior. We have empirically evaluated CARE on various tasks such as backdoor removal, neural network repair for fairness and safety properties. Our experiment results show that CARE is able to repair all neural networks efficiently and effectively. For fairness repair tasks, CARE successfully improves fairness by 61.91% on average. For backdoor removal tasks, CARE reduces the attack success rate from over 98% to less than 1%. For safety property repair tasks, CARE reduces the property violation rate to less than 1%. Results also show that thanks to the causality-based fault localization, CARE's repair focuses on the misbehavior and preserves the accuracy of the neural networks.
Featured Cover Oh, Myeongchan; Lee, Jehyun; Kim, Jin‐Young ...
Wind energy (Chichester, England),
June 2022, 2022-06-00, 20220601, Volume:
25, Issue:
6
Journal Article
Peer reviewed
Open access
The cover image is based on the Research Article Machine learning‐based statistical downscaling of wind resource maps using multi‐resolution topographical data by Myeongchan Oh et al., ...https://doi.org/10.1002/we.2718.
Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, ...hardware and software system failures, and malware detection. In these contexts, model interpretability is vital for administrator and analyst to trust and act on the automated analysis of machine learning models. Deep learning methods have been criticized as black box oracles which allow limited insight into decision factors. In this work we seek to bridge the gap between the impressive performance of deep learning models and the need for interpretable model introspection. To this end we present recurrent neural network (RNN) language models augmented with attention for anomaly detection in system logs. Our methods are generally applicable to any computer system and logging source. By incorporating attention variants into our RNN language models we create opportunities for model introspection and analysis without sacrificing state-of-the art performance. We demonstrate model performance and illustrate model interpretability on an intrusion detection task using the Los Alamos National Laboratory (LANL) cyber security dataset, reporting upward of 0.99 area under the receiver operator characteristic curve despite being trained only on a single day's worth of data.