[20/01/25] At Écoles des Mines Saint-Étienne On "Shaping the future of industrial decision-making with Artificial Intelligence, A research-industry perspective", Saint-Étienne
Preprints, Journal and Conference Papers
Ezukwoke, K., Hoayek, A., Batton-Hubert, M., & Boucher, X. (2022). GCVAE: Generalized-Controllable Variational AutoEncoder. arXiv. https://arxiv.org/abs/2206.04225
@misc{gcvae,
doi = {10.48550/ARXIV.2206.04225},
url = {https://arxiv.org/abs/2206.04225},
author = {Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier},
keywords = {Machine Learning (stat.ML), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences, 62F15, 62F30},
title = {GCVAE: Generalized-Controllable Variational AutoEncoder},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}
Variational autoencoders (VAEs) have recently been used for unsupervised disentanglement learning of complex density distributions. Numerous variants exist to encourage disentanglement in latent space while improving reconstruction. However, none have simultaneously managed the trade-off between attaining extremely low reconstruction error and a high disentanglement score. We present a generalized framework to handle this challenge under constrained optimization and demonstrate that it outperforms state-of-the-art existing models as regards disentanglement while balancing reconstruction. We introduce three controllable Lagrangian hyperparameters to control reconstruction loss, KL divergence loss and correlation measure. We prove that maximizing information in the reconstruction network is equivalent to information maximization during amortized inference under reasonable assumptions and constraint relaxation.
Ezukwoke, K., Hoayek, A., Batton-Hubert, M., Boucher, X., Gounet, P., & Adrian, J. (2022). Leveraging Pre-trained Models for Failure Analysis Triplets Generation. arXiv. https://arxiv.org/abs/2210.17497
@misc{fatg,
doi = {10.48550/ARXIV.2210.17497},
url = {https://arxiv.org/abs/2210.17497},
author = {Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier and Gounet, Pascal and Adrian, Jerome},
keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), Applications (stat.AP), FOS: Computer and information sciences, FOS: Computer and information sciences, G.3; I.2; I.7, 68Txx, 68Uxx},
title = {Leveraging Pre-trained Models for Failure Analysis Triplets Generation},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
Pre-trained Language Models recently gained traction in the Natural Language Processing (NLP) domain for text summarization, generation and question-answering tasks. This stems from the innovation introduced in Transformer models and their overwhelming performance compared with Recurrent Neural Network Models (Long Short Term Memory (LSTM)). In this paper, we leverage the attention mechanism of pre-trained causal language models such as Transformer model for the downstream task of generating Failure Analysis Triplets (FATs) - a sequence of steps for analyzing defected components in the semiconductor industry. We compare different transformer models for this generative task and observe that Generative Pre-trained Transformer 2 (GPT2) outperformed other transformer model for the failure analysis triplet generation (FATG) task. In particular, we observe that GPT2 (trained on 1.5B parameters) outperforms pre-trained BERT, BART and GPT3 by a large margin on ROUGE. Furthermore, we introduce Levenshstein Sequential Evaluation metric (LESE) for better evaluation of the structured FAT data and show that it compares exactly with human judgment than existing metrics.
Ezukwoke, K., Hoayek, A., Batton-Hubert, M., Boucher, X., Gounet, P., & Adrian, J. (2024). Big GCVAE: decision-making with adaptive transformer model for failure root cause analysis in semiconductor industry. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-024-02346-x
@article{Ezukwoke2024,
author = {Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier and Gounet, Pascal and Adrian, J{\'e}r{\^o}me},
title = {Big GCVAE: decision-making with adaptive transformer model for failure root cause analysis in semiconductor industry},
journal = {Journal of Intelligent Manufacturing},
year = {2024},
month = apr,
day = {02},
issn = {1572-8145},
doi = {10.1007/s10845-024-02346-x},
url = {https://doi.org/10.1007/s10845-024-02346-x}
}
Pre-trained large language models (LLMs) have gained significant attention in the field of natural language processing (NLP), especially for the task of text summarization, generation, and question answering. The success of LMs can be attributed to the attention mechanism introduced in Transformer models, which have outperformed traditional recurrent neural network models (e.g., LSTM) in modeling sequential data. In this paper, we leverage pre-trained causal language models for the downstream task of failure analysis triplet generation (FATG), which involves generating a sequence of failure analysis decision steps for identifying failure root causes in the semiconductor industry. In particular, we conduct extensive comparative analysis of various transformer models for the FATG task and find that the BERT-GPT-2 Transformer (Big GCVAE), fine-tuned on a proposed Generalized-Controllable Variational AutoEncoder loss (GCVAE), exhibits superior performance in generating informative latent space by promoting disentanglement of latent factors. Specifically, we observe that fine-tuning the Transformer style BERT-GPT2 on the GCVAE loss yields optimal representation by reducing the trade-off between reconstruction loss and KL-divergence, promoting meaningful, diverse and coherent FATs similar to expert expectations.
Wang, Z., Ezukwoke, K., Hoayek, A., Batton-Hubert, M., & Boucher, X. (2023). Natural language processing (NLP) and association rules (AR)-based knowledge extraction for intelligent fault analysis: a case study in semiconductor industry. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-023-02245-7
@article{Wang2023,
author = {Wang, Zhiqiang and Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier},
title = {Natural language processing (NLP) and association rules (AR)-based knowledge extraction for intelligent fault analysis: a case study in semiconductor industry},
journal = {Journal of Intelligent Manufacturing},
year = {2023},
month = dec,
day = {30},
issn = {1572-8145},
doi = {10.1007/s10845-023-02245-7},
url = {https://doi.org/10.1007/s10845-023-02245-7}
}
Fault analysis (FA) is the process of collecting and analyzing data to determine the cause of a failure. It plays an important role in ensuring the quality in manufacturing process. Traditional FA techniques are time-consuming and labor-intensive, relying heavily on human expertise and the availability of failure inspection equipment. In semiconductor industry, a large amount of FA reports are generated by experts to record the fault descriptions, fault analysis path and fault root causes. With the development of Artificial Intelligence, it is possible to automate the industrial FA process while extracting expert knowledge from the vast FA report data. The goal of this research is to develop a complete expert knowledge extraction pipeline for FA in semiconductor industry based on advanced Natural Language Processing and Machine Learning. Our research aims at automatically predicting the fault root cause based on the fault descriptions. First, the text data from the FA reports are transformed into numerical data using Sentence Transformer embedding. The numerical data are converted into latent spaces using Generalized-Controllable Variational AutoEncoder. Then, the latent spaces are classified by Gaussian Mixture Model. Finally, Association Rules are applied to establish the relationship between the labels in the latent space of the fault descriptions and that of the fault root cause. The proposed algorithm has been evaluated with real data of semiconductor industry collected over three years. The average correctness of the predicted label achieves 97.8%. The method can effectively reduce the time of failure identification and the cost during the inspection stage.
Rammal, A., Ezukwoke, K., Hoayek, A., & Batton-Hubert, M. (2023). Root cause prediction for failures in semiconductor industry, a genetic algorithm–machine learning approach. Scientific Reports, 13(1), 4934.
@article{rammal2023root,
title = {Root cause prediction for failures in semiconductor industry, a genetic algorithm--machine learning approach},
author = {Rammal, Abbas and Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille},
journal = {Scientific Reports},
volume = {13},
number = {1},
pages = {4934},
year = {2023},
publisher = {Nature Publishing Group UK London}
}
Failure analysis has become an important part of guaranteeing good quality in the electronic component manufacturing process. The conclusions of a failure analysis can be used to identify a component’s flaws and to better understand the mechanisms and causes of failure, allowing for the implementation of remedial steps to improve the product’s quality and reliability. A failure reporting, analysis, and corrective action system is a method for organizations to report, classify, and evaluate failures, as well as plan corrective actions. These text feature datasets must first be preprocessed by Natural Language Processing techniques and converted to numeric by vectorization methods before starting the process of information extraction and building predictive models to predict failure conclusions of a given failure description. However, not all-textual information is useful for building predictive models suitable for failure analysis. Feature selection has been approached by several variable selection methods. Some of them have not been adapted for use in large data sets or are difficult to tune and others are not applicable to textual data. This article aims to develop a predictive model able to predict the failure conclusions using the discriminating features of the failure descriptions. For this, we propose to combine a Genetic Algorithm with supervised learning methods for an optimal prediction of the conclusions of failure in terms of the discriminant features of failure descriptions. Since we have an unbalanced dataset, we propose to apply an F1 score as a fitness function of supervised classification methods such as Decision Tree Classifier and Support Vector Machine. The suggested algorithms are called GA-DT and GA-SVM. Experiments on failure analysis textual datasets demonstrate the effectiveness of the proposed GA-DT method in creating a better predictive model of failure conclusion compared to using the information of the entire textual features or limited features selected by a genetic algorithm based on a SVM. Quantitative performances such as BLEU score and cosine similarity are used to compare the prediction performance of the different approaches.
Rammal, A., Ezukwoke, K., Hoayek, A., & Batton-Hubert, M. (2023). Unsupervised approach for an optimal representation of the latent space of a failure analysis dataset. The Journal of Supercomputing, 1–27.
@article{rammal2023replearn,
title = {Unsupervised approach for an optimal representation of the latent space of a failure analysis dataset},
author = {Rammal, Abbas and Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille},
journal = {The Journal of Supercomputing},
volume = {},
number = {},
pages = {1-27},
year = {2023},
doi = {10.1007/s11227-023-05634-0}
}
Microelectronics production failure analysis is an important step in improving product quality and development. In fact, the understanding of the failure mechanisms and therefore the implementation of corrective actions on the cause of the failure depend on the results of this analysis. These analyses are saved under textual features format. Then such data need first to be preprocessed and vectorized (converted to numeric). Second, to overcome the curse of dimensionality caused by the vectorisation process, a dimension reduction is applied. A two-stage variable selection and feature extraction is used to reduce the high dimensionality of a feature space. We are first interested in studying the potential of using an unsupervised variable selection technique, the genetic algorithm, to identify the variables that best demonstrate discrimination in the separation and compactness of groups of textual data. The genetic algorithm uses a combination of the K-means or Gaussian Mixture Model clustering and validity indices as a fitness function for optimization. Such a function improves both compactness and class separation. The second work looks into the feasibility of applying a feature extraction technique. The adopted methodology is a Deep learning algorithm based on variational autoencoder (VAE) for latent space disentanglement and Gaussian Mixture Model for clustering of the latent space for cluster identification. The last objective of this paper is to propose a new methodology based on the combination between variational autoencoder (VAE) for the latent space disentanglement, and genetic algorithm (GA) to find, in an unsupervised way, the latent variables allowing the best discrimination of clusters of failure analysis data. This methodology is called VAE-GA. Experiments on textual datasets of failure analysis demonstrate the effectiveness of the VAE-GA proposed method which allows better discrimination of textual classes compared to the use of GA or VAE separately or the combination of PCA with GA (PCA-GA) or a simple Auto-encoders with GA (AE-GA).
Ezukwoke, K. I., & Zareian, S. J. (2021). Online Learning and Active Learning: A Comparative Study of Passive-Aggressive Algorithm With Support Vector Machine (SVM). Journal of Higher Education Theory and Practice, 21(3). https://articlegateway.com/index.php/JHETP/article/view/4152
@article{Ezukwoke_Zareian_2021,
title = {Online Learning and Active Learning: A Comparative Study of Passive-Aggressive Algorithm With Support Vector Machine (SVM)},
volume = {21},
url = {https://articlegateway.com/index.php/JHETP/article/view/4152},
doi = {10.33423/jhetp.v21i3.4152},
abstractnote = {<p>Passive aggressive online learning is an extension of Support Vector Machine (SVM) to the context of online learning for binary classification. In this paper we consider the application of the algorithm on anomaly labeling for IJCNN 2001 Neural Network Competition dataset from LibSVM dataset repository1 from Ford Research Laboratory. We also work on an improved version of the online learning algorithm called Active learning and we compare both algorithms to that of SVM (from LibSVM library). We propose different experimental setups for comparing the algorithms.</p>},
number = {3},
journal = {Journal of Higher Education Theory and Practice},
author = {Ezukwoke, K.I and Zareian, S.J},
year = {2021},
month = jun
}
Wang, Z., Ezukwoke, K., Hoayek, A., Batton-Hubert, M., & Boucher, X. (2022). NLP based on GCVAE for intelligent Fault Analysis in Semiconductor industry. IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), 1–8.
@inproceedings{gcvae_etfa,
author = {Wang, Zhiqiang and Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier},
booktitle = {IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)},
title = {NLP based on GCVAE for intelligent Fault Analysis in Semiconductor industry},
year = {2022},
volume = {},
number = {},
pages = {1-8},
doi = {10.1109/ETFA52439.2022.9921524}
}
In the semiconductor industry, Failure Analysis (FA) is an investigation to determine the root causes of a failure. It also involves an intermediate analysis to build the steps of the failure analysis in order to mitigate future failures and to facilitate the future FA. In the framework of the FA 4.0 project, the reporting system records three items of information using natural language: the failure analysis request description (input space) and analysis steps (paths), as well as generic categories of root cause conclusion (output space). The main objective of this article is to develop a system which is able to automatically help industries carry out fault analysis diagnoses with Artificial intelligence (AI). This article extends and validates the adapted methodology proposed by [1] to transform text data into numeric data based on Natural Language Processing (NLP). It transforms the text data from the input space and output space. Different deep learning algorithms based on a Variational AutoEncoder (VAE) are applied to the output space to reduce the dimension of the numeric data, and the performance of each VAE is evaluated with different metrics. The Generalized-Controllable VAE (GCVAE) is the one best suited to our case. A Gaussian Mixture Model (GMM) is then used to perform clustering in the latent space generated by the GCVAE. A centroid analysis is also conducted to verify the similarity of each cluster.
Rammal, A., Ezukwoke, K., Hoayek, A., & Batton-Hubert, M. (2022). Unsupervised Variable Selection Using a Genetic Algorithm: An Application to Textual Data. IEEE International Conference on Smart Systems and Power Management (IC2SPM), 11–19.
@inproceedings{ga_ic2spm,
author = {Rammal, Abbas and Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille},
booktitle = {IEEE International Conference on Smart Systems and Power Management (IC2SPM)},
title = {Unsupervised Variable Selection Using a Genetic Algorithm: An Application to Textual Data},
year = {2022},
volume = {},
number = {},
pages = {11-19},
doi = {10.1109/IC2SPM56638.2022.9989008}
}
Microelectronics production failure analysis is an important step in improving product quality and development. Indeed, the understanding of the failure mechanisms and therefore the implementation of corrective actions on the cause of the failure depend on the results of these analysis. These analysis are saved under textual features format. Then such data need first to be pre-processed and vectorized (converted to numeric). Second, to overcome the curse of dimensionality caused by the vectorisation process, a dimension reduction is applied. We are first interested in studying the potential of using an unsupervised variable selection technique to identify the variables that best demonstrate discrimination in the separation and compactness of groups of textual data. Variable selection has been approached by several variable or feature selection methods. Some of them have not been adapted for use in large data sets or are difficult to tune, and others require additional information. This work investigates the potential of using a genetic algorithm to find, in an unsupervised way, the variables allowing the best discrimination of the classes, to select variables correlated to particular textual groups. The proosed genetic algorithm uses a combination of the K-means clustering and validity indices as a fitness function for optimization. Such a function improves both compactness and class separation. Experiments on textual datasets demonstrate the effectiveness of the proposed method of variable selection which allows better discrimination of textual classes compared to the use of K-means clustering on all data variables.
Ezukwoke, K., Toubakh, H., Hoayek, A., Batton-Hubert, M., Boucher, X., & Gounet, P. (2021). Intelligent Fault Analysis Decision Flow in Semiconductor Industry 4.0 Using Natural Language Processing with Deep Clustering. IEEE 17th International Conference on Automation Science and Engineering (CASE), 429–436.
@inproceedings{FAnlp_ieeecase,
author = {Ezukwoke, Kenneth and Toubakh, Houari and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier and Gounet, Pascal},
booktitle = {IEEE 17th International Conference on Automation Science and Engineering (CASE)},
title = {Intelligent Fault Analysis Decision Flow in Semiconductor Industry 4.0 Using Natural Language Processing with Deep Clustering},
year = {2021},
volume = {},
number = {},
pages = {429-436},
doi = {10.1109/CASE49439.2021.9551492}
}
Microelectronics production failure analysis is a time-consuming and complicated task involving successive steps of analysis of complex process chains. The analysis is triggered to find the root cause of a failure and its findings, recorded in a reporting system using natural language. Fault analysis, physical analysis, sample preparation and package construction analysis are arguably the most used analysis activity for determining the root-cause of a failure. Intelligent automation of this analysis decision process using artificial intelligence is the objective of the FA 4.0 consortium; creating a reliable and efficient semiconductor industry. This research presents natural language processing (NLP) techniques to find a coherent representation of the expert decisions during fault analysis. The adopted methodology is a Deep learning algorithm based on β -variational autoencoder (β -VAE) for latent space disentanglement and Gaussian Mixture Model for clustering of the latent space for class identification.
Ezukwoke, K., Hoayek, A., Batton-Hubert, M., Boucher, X., & Gounet, P. (2021). β-Variational AutoEncoder and Gaussian Mixture Model for Fault Analysis Decision Flow in Semiconductor Industry 4.0. ENBIS 2021 Spring Meeting. Poster. https://hal-emse.ccsd.cnrs.fr/emse-03524369
@inproceedings{enbis,
title = {$\beta$ -Variational AutoEncoder and Gaussian Mixture Model for Fault Analysis Decision Flow in Semiconductor Industry 4.0},
author = {Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier and Gounet, Pascal},
url = {https://hal-emse.ccsd.cnrs.fr/emse-03524369},
note = {Poster},
booktitle = {ENBIS 2021 Spring Meeting},
address = {Online, France},
year = {2021},
hal_id = {emse-03524369},
hal_version = {v1}
}
Failure analysis (FA) is key to a reliable semiconductor industry. Fault analysis, physical analysis, sample preparation and package construction analysis are arguably the most used analysis activity for determining the root-cause of a failure in semiconductor industry 4.0. As a result, intelligent automation of this analysis decision process using artificial intelligence is the objective of the Industry 4.0 consortium. The research presents natural language processing (NLP) techniques to find a coherent representation of the expert decisions during fault analysis using β-variational autoencoder (β-VAE) for space disentanglement or class discrimination and Gaussian Mixture Model for clustering of the latent space for class identification.
Regular and Invited talks
Ezukwoke, K., Hoayek, A., Batton-Hubert, M., & Boucher, X. (2022). Artificial intelligence for Fault Analysis in Semiconductor Industry. Highlight: Generalized-Controllable Variational AutoEncoder (GCVAE). Plate-Forme Intelligence Artificielle (PFIA-22). https://arxiv.org/abs/2206.04225
@incollection{gcvae_talk,
doi = {10.48550/ARXIV.2206.04225},
url = {https://arxiv.org/abs/2206.04225},
author = {Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier},
keywords = {invited},
title = {Artificial intelligence for Fault Analysis in Semiconductor Industry. Highlight: Generalized-Controllable Variational AutoEncoder (GCVAE)},
publisher = {Plate-Forme Intelligence Artificielle (PFIA-22)},
year = {2022}
}
Variational autoencoders (VAEs) have recently been used for unsupervised disentanglement learning of complex density distributions. Numerous variants exist to encourage disentanglement in latent space while improving reconstruction. However, none have simultaneously managed the trade-off between attaining extremely low reconstruction error and a high disentanglement score. We present a generalized framework to handle this challenge under constrained optimization and demonstrate that it outperforms state-of-the-art existing models as regards disentanglement while balancing reconstruction. We introduce three controllable Lagrangian hyperparameters to control reconstruction loss, KL divergence loss and correlation measure. We prove that maximizing information in the reconstruction network is equivalent to information maximization during amortized inference under reasonable assumptions and constraint relaxation.
Ezukwoke, K., Hoayek, A., Batton-Hubert, M., & Boucher, X. (2022). Deep Generative Model. Highlight: Generalized-Controllable Variational AutoEncoder (GCVAE). Seminar at GMI/DSI-LIMOS/MAAD-LIMOS, Mines Saint-Étienne. https://arxiv.org/abs/2206.04225
@incollection{gcvae_tall,
doi = {10.48550/ARXIV.2206.04225},
url = {https://arxiv.org/abs/2206.04225},
author = {Ezukwoke, Kenneth and Hoayek, Anis and Batton-Hubert, Mireille and Boucher, Xavier},
keywords = {regular},
title = {Deep Generative Model. Highlight: Generalized-Controllable Variational AutoEncoder (GCVAE)},
publisher = {Seminar at GMI/DSI-LIMOS/MAAD-LIMOS, Mines Saint-Étienne},
year = {2022}
}
Variational AutoEncoders (VAEs) have recently been used for unsupervised disentanglement learning of overlapping mixtures of distributions (e.g Gaussian). Numerous variants exist to encourage disentanglement in hidden (latent) spaces while improving reconstruction quality. However, none have simultaneously managed the trade-off between attaining extremely low reconstruction error and a high disentanglement score. We present a generalized framework to handle this challenge under constrained optimization and demonstrate that it outperforms state-of-the-art existing models as regards disentanglement while balancing reconstruction. We will begins first by introducing you to the formalization of variational autoencoders and their closed form solution followed by a more stable version, Generalized Variational Autoencoder (GCVAE).
Teaching
Lecturer (Teaching Fellow), École des Mines de Saint-Étienne (EMSE)
Mathematical methods for large dimensions (Big data clustering) – 2022, 2023
Mathematical methods for large dimensions (Introduction to Natural Language Processing) – 2022, 2023
Teaching Assistant, École des Mines de Saint-Étienne (EMSE)
Deep Learning (introducton to deep learning based on Tensorflow library) practical class – 2021
Numerical Methods (construction and testing of the Finite Difference solver) practical class – 2021, 2022, 2023.
Services
Reviewer
WiML, IEEE CASE, EMNLP, AISTATS, ACL.
Volunteering
(April 25-29, 2022) The 10th International Conference on Learning Representations (ICLR-22), Virtual
(March 28-30, 2022) The 25th International Conference on Artificial Intelligence and Statistics (AISTATS-22), Virtual
(Aug. 23-27, 2021) IEEE International Conference on Automation Science and Engineering (IEEE CASE-21), Lyon, FR
(April 13-15, 2021) The 24th International Conference on Artificial Intelligence and Statistics (AISTATS-21), Virtual
Mentoring
(Oct. 2020 - 2021) Mentor on AI for Coral Reef Conservation in the Vamizi Island, Mozambique (AI for Coral Reef)
