Autoencoder Research Articles

Computer Modelling of Textures on Images with Human Skin Wound Areas

In this paper, we concentrate on the images of the wounds on the human skin and propose to consider each image as a set of smaller pieces – crops or patches containing different textures. We overview, develop and compare deep learning feature extraction methods to model image crops as 200-dimensional feature vectors using various artificial neural network architectures: convolutional autoencoders, variational convolutional autoencoders, and Siamese convolutional networks trained in the contrastive learning manner. Also, we develop a custom convolutional encoder and decoder, use them in the aforementioned architectures and compare them with the ResNet encoder and decoder alternatives. Finally, we train and evaluate k-nearest neighbors and Multi-Layer Perceptron classifiers on the features extracted with the model above options to discriminate skin, wound, and background image patches. Classification evaluation results on the features, extracted with the Siamese network, show the best test accuracy for all implementations without a significant shift between model versions (accuracy > 93%); variational autoencoders show random results for all options (accuracy around 33%), and convolutional autoencoders reached good results (accuracy > 77%) but with a noticeable difference between the custom and ResNet versions; the latter is better. Custom encoder and decoder implementations are faster and smaller than the ResNet alternatives but may be less stable on larger datasets, which still needs investigation. Possible applications of the feature vectors include an area of interest extraction during wound segmentation or classification and usage as patch embeddings while training vision transformer architectures.

A novel reinforcement learning agent for rotating machinery fault diagnosis with data augmentation

The problem of data imbalance and limited sample poses a prominent challenge to fault diagnosis in industry, especially in rotating machinery fault diagnosis due to the constraints of sampling and labeling. Reinforcement learning is known for its auto-optimized learning ability but it is severely limited by the quality and quantity of data it is able to collect. This paper applies the Equilibrium Deep Q-Network (Equilibrium-DQN) based agent with the Variational Autoencoder with Wasserstein Generative Adversarial Network and Gradient Penalty (VAE-WGAN-GP) for rotating machinery fault diagnosis. The Equilibrium-DQN possesses the property of leveraging multiple target networks to improve training stability and accuracy. The VAE-WGAN-GP excels in resolving data scarcity problems in fault diagnosis, especially in enriching labeled data with more typical samples while keeping the original data features. Herein, a novel framework is presented that integrates both data augmentation techniques with reinforcement learning agent for fault diagnosis. The proposed framework improves the weakness of insufficient samples in fault diagnosis and reveals its potential in complex industrial applications. The experiments, both on the test bench dataset and on the real locomotive dataset, confirm the advantage of the proposed framework.

Enhancing Planning for Autonomous Driving via an Iterative Optimization Framework Incorporating Safety-Critical Trajectory Generation

Ensuring the safety of autonomous vehicles (AVs) in complex and high-risk traffic scenarios remains a critical unresolved challenge. Current AV planning methods exhibit limitations in generating robust driving trajectories that effectively avoid collisions, highlighting the urgent need for improved planning strategies to address these issues. This paper introduces a novel iterative optimization framework that incorporates safety-critical trajectory generation to enhance AV planning. The use of the HighD dataset, which is collected using the wide-area remote sensing capabilities of unmanned aerial vehicles (UAVs), is fundamental to the framework. Remote sensing enables large-scale real-time observation of traffic conditions, providing precise data on vehicle dynamics, road structures, and surrounding environments. To generate safety-critical trajectories, the decoder within the conditional variational auto-encoder (CVAE) is innovatively designed through a data-mechanism integration method, ensuring that these trajectories strictly adhere to vehicle kinematic constraints. Furthermore, two parallel CVAEs (Dual-CVAE) are trained collaboratively by a shared objective function to implicitly model the multi-vehicle interactions. Inspired by the concept of “learning to collide”, adversarial optimization is integrated into the Dual-CVAE (Adv. Dual-CVAE), facilitating efficient generation from normal to safety-critical trajectories. Building upon this, these generated trajectories are then incorporated into an iterative optimization framework, significantly enhancing the AV’s planning ability to avoid collisions. This framework decomposes the optimization process into stages, initially addressing normal trajectories and progressively tackling more safety-critical and collision trajectories. Finally, comparative case studies of enhancing AV planning are conducted and the simulation results demonstrate that the proposed method can efficiently enhance AV planning by generating safety-critical trajectories.

Advanced Deep Learning Techniques for Information Security Vulnerability Detection Using Machine Learning

The increasing rate on the complexity and amount of security threats demand more advanced information security vulnerability detection techniques. Traditional methods have limited capability to respond to such diverse and evolving threats in real-time. This paper presents a complete solution by using new machine learning models in combine with advanced mathematical approaches to organize the early detection and prediction of vulnerabilities that later content will be about the information security systems. We investigate the accuracy of different models (with an emphasis on modern approaches that go beyond the standard SVM, CNN, and GNN). It initiates with Bayesian Networks that use probabilistic graphical models for showing the interactions of diverse security characteristics to support reasoning about vulnerabilities as a function on the conditional dependencies. Decision Trees and ensemble techniques like Extreme Gradient Boosting (XGBoost) are able to deal with both heterogeneous data types and are more capable of modelling complex interaction between security features. For unsupervised cases, we use things like Isolation Forests for anomaly detection and Gaussian Mixture Models (GMM) to detect rare patterns in network packets that may be a sign of security attacks. We further investigate the possibility of reinforcement learning (i.e., Q-Learning) to continue to evolve with network changes and identify threats in real-world threatening environment. The learning process is streamlined and the interpretability of results is improved by integrating mathematical techniques such as Markov Chains (for modelling probabilistic transitions within network states) and optimization methods like Lasso Regression (for feature selection). In addition to this, the approach explores Autoencoder-based models but most specifically Variational Autoencoders (VAEs) for their unsupervised learning ability in identifying rare and new zero-day vulnerabilities. Extensive experiments on a variety of cybersecurity datasets demonstrate the effectiveness and efficiency of our approach, where substantial enhancements in detection speed and accuracy are achieved. The cloud-based cybersecurity model introduced in this research, backed by advanced machine learning models and mathematical frameworks could potentially serve to lay a foundation for the future of real-time cyber security defence mechanisms.

A deep learning approach for non-invasive Alzheimer’s monitoring using microwave radar data

Over 50 million people globally suffer from Alzheimer’s disease (AD), emphasizing the need for efficient, early diagnostic tools. Traditional methods like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) scans are expensive, bulky, and slow. Microwave-based techniques offer a cost-effective, non-invasive, and portable solution, diverging from conventional neuroimaging practices. This article introduces a deep learning approach for monitoring AD , using realistic numerical brain phantoms to simulate scattered signals via the CST Studio Suite. The obtained data is preprocessed using normalization, standardization, and outlier removal to ensure data integrity. Furthermore, we propose a novel data augmentation technique to enrich the dataset across various AD stages. Our deep learning approach combines Recursive Feature Elimination (RFE) with Principal Component Analysis (PCA) and Autoencoders (AE) for optimal feature selection. Convolution Neural Network (CNN) is combined with Gated Recurrent Unit (GRU), Bidirectional Long Short Term Memory (Bidirectional-LSTM), and Long Short-Term Memory (LSTM) to improve classification performance. The integration of RFE-PCA-AE significantly elevates performance, with the CNN+GRU model achieving an 87% accuracy rate, thus outperforming existing studies.

Unsupervised few shot learning architecture for diagnosis of periodontal disease in dental panoramic radiographs.

In the domain of medical imaging, the advent of deep learning has marked a significant progression, particularly in the nuanced area of periodontal disease diagnosis. This study specifically targets the prevalent issue of scarce labeled data in medical imaging. We introduce a novel unsupervised few-shot learning algorithm, meticulously crafted for classifying periodontal diseases using a limited collection of dental panoramic radiographs. Our method leverages UNet architecture for generating regions of interest (RoI) from radiographs, which are then processed through a Convolutional Variational Autoencoder (CVAE). This approach is pivotal in extracting critical latent features, subsequently clustered using an advanced algorithm. This clustering is key in our methodology, enabling the assignment of labels to images indicative of periodontal diseases, thus circumventing the challenges posed by limited datasets. Our validation process, involving a comparative analysis with traditional supervised learning and standard autoencoder-based clustering, demonstrates a marked improvement in both diagnostic accuracy and efficiency. For three real-world validation datasets, our UNet-CVAE architecture achieved up to average 14% higher accuracy compared to state-of-the-art supervised models including the vision transformer model when trained with 100 labeled images. This study not only highlights the capability of unsupervised learning in overcoming data limitations but also sets a new benchmark for diagnostic methodologies in medical AI, potentially transforming practices in data-constrained scenarios.

Deep Learning with Crested Porcupine Optimizer for Detection and Classification of Paddy Leaf Diseases for Sustainable Agriculture

India has a vast number of inhabitants and the main food source distribution is from agriculture. Agricultural lands are being demolished generally owing to plant and crop illnesses. The detection of plant diseases by using image processing models can aid agriculturalists in defending the farming area from damaging or affecting it. Paddy is the main harvest worldwide. Early recognition of the paddy diseases at dissimilar phases of development is very vital in paddy production. However, the present manual technique in identifying and classifying paddy diseases needs a very educated farmer and is time-consuming. Deep learning (DL) is an effectual research area in the classification of agriculture patterns where it can efficiently solve the problems of diseases identification. Therefore, the articles focus on the design and expansion of Deep Learning based Crested Porcupine Optimizer for the Detection and Classification of Paddy Leaf Diseases (DLCPO-DCPLD) method for Sustainable Agriculture. The main aim of the DLCPO-DCPLD method use DL method for the recognition and identification of rice plant leaf diseases. To accomplish this, the DLCPO-DCPLD technique performs the image pre-processing using Median Filtering (MF) to recover the excellence of the input frames. Next, the ConvNeXt-L method is applied for extraction of feature vectors from the pre-processed images. Also, the Conditional Variational Autoencoder (CVAE) model is utilized for the automated classification of Paddy Leaf diseases. Eventually, the hyperparameter tuning of the CVAE technique is accomplished by implementing the Crested Porcupine Optimizer (CPO) technique. To safeguard the enhanced predictive results of the DLCPO-DCPLD method, a sequence of experimentations is implemented on the benchmark dataset. The experimental validation of the DLCPO-DCPLD method portrayed a superior accuracy value of 99.12% over existing approaches.

Cramer Distance: A Deep Learning Approach for Better Epileptic Seizure Prediction

Epilepsy is a neurological condition that is found in most people all over the world, and the ability to accurately anticipate seizures in epileptic patients has a significant impact on both their level of protection and their overall quality of life. This research proposes a unique patient specific seizure prediction approach based on Deep Learning (DL) using long-term scalp electroencephalogram (EEG) recordings to predict seizure onset. Preictal brain states should be adequately detected and differentiated from the prevalent interictal brain states as early as possible to make this technology acceptable for real-time use. A single automated system has been designed for the Features Extraction (FE) and classification processes. The raw EEG signal that has not been pre-processed is considered the input to the system, and the signal is further reduced using subsequent computations. An innovative reconstruction approach using Variational Auto-Encoder Generative Adversarial Networks (VAE+C+GAN) with the Cramer Distance (CD) and a Temporal-Spatial-Frequency (TSF) loss function is presented in this research work. The machine that discriminates receives instructions to differentiate between created tests and actual samples, while the generator is verified to produce false samples that the discriminator does not recognize as fake. The proposed VAE+C+GAN’s experimental results have been examined, and a classification accuracy of 95% has been achieved. According to the experiment's findings, the VAE-C-GAN performs better than the current EEG classification system and has excellent potential for real-time applications.

Diverse non-homogeneous texture synthesis from a single exemplar

Capturing non-local, long range features present in non-homogeneous textures is difficult to achieve with existing techniques. We introduce a new training method and architecture for single-exemplar texture synthesis that combines a Generative Adversarial Network (GAN) and a Variational Autoencoder (VAE). In the proposed architecture, the combined networks share information during training via structurally identical, independent blocks, facilitating highly diverse texture variations from a single image exemplar. Supporting this training method, we also include a similarity loss term that further encourages diverse output while also improving the overall quality. Using our approach, it is possible to produce diverse results over the entire sample size taken from a single model that can be trained in approximately 15 min. We show that our approach obtains superior performance when compared to SOTA texture synthesis methods and single image GAN methods using standard diversity and quality metrics.

BaHaMAs: a method for uncertainty quantification in geodetic time series and its application in short-term prediction of length of day

Some of the important geodetic time series used in various Earth science disciplines are provided without uncertainty estimates. This can affect the validity of conclusions based on such data. However, an efficient uncertainty quantification algorithm to tackle this problem is currently not available. Here we present a methodology to approximate the aleatoric uncertainty in time series, called Bayesian Hamiltonian Monte Carlo Autoencoders (BaHaMAs). BaHaMAs is based on three elements: (1) self-supervised autoencoders that learn the underlying structure of the time series, (2) Bayesian machine learning that accurately quantifies the data uncertainty, and (3) Monte Carlo sampling that follows the Hamiltonian dynamics. The method can be applied in various fields in the Earth sciences. As an example, we focus on Atmospheric and Oceanic Angular Momentum time series (AAM and OAM, respectively), which are typically provided without uncertainty information. We apply our methodology to 3-hourly AAM and OAM time series and quantify the uncertainty in the data from 1976 up to the end of 2022. Furthermore, since Length of Day (LOD) is a geodetic time series that is closely connected to AAM and OAM and its short-term prediction is important for various space-geodetic applications, we show that the use of the derived uncertainties alongside the time series of AAM and OAM improves the prediction performance of LOD on average by 17% for different time spans. Finally, a comparison with alternative uncertainty quantification baseline methods, i.e., variational autoencoders and deep ensembles, reveals that BaHaMAs is more accurate in quantifying uncertainty.Graphical

Variational Autoencoder with Gaussian Random Field prior: Application to unsupervised animal detection in aerial images

In real world datasets of aerial images, the objects of interest are often missing, hard to annotate and of varying aspects. The framework of unsupervised Anomaly Detection (AD) is highly relevant in this context, and Variational Autoencoders (VAEs), a family of popular probabilistic models, are often used. We develop on the literature of VAEs for AD in order to take advantage of the particular textures that appear in natural aerial images. More precisely we propose a new VAE model with a Gaussian Random Field (GRF) prior (VAE-GRF), which generalizes the classical VAE model, and we provide the necessary procedures and hypotheses required for the model to be tractable. We show that, under some assumptions, the VAE-GRF largely outperforms the traditional VAE and some other probabilistic models developed for AD. Our results suggest that the VAE-GRF could be used as a relevant VAE baseline in place of the traditional VAE with very limited additional computational cost. We provide competitive results on the MVTec reference dataset for visual inspection, and two other datasets dedicated to the task of unsupervised animal detection in aerial images.

Unsupervised machine learning model for detecting anomalous volumetric modulated arc therapy plans for lung cancer patients.

Volumetric modulated arc therapy (VMAT) is a new treatment modality in modern radiotherapy. To ensure the quality of the radiotherapy plan, a physics plan review is routinely conducted by senior clinicians; however, this process is less efficient and less accurate. In this study, a multi-task AutoEncoder (AE) is proposed to automate anomaly detection of VMAT plans for lung cancer patients. The feature maps are first extracted from a VMAT plan. Then, a multi-task AE is trained based on the input of a feature map, and its output is the two targets (beam aperture and prescribed dose). Based on the distribution of reconstruction errors on the training set, a detection threshold value is obtained. For a testing sample, its reconstruction error is calculated using the AE model and compared with the threshold value to determine its classes (anomaly or regular). The proposed multi-task AE model is compared to the other existing AE models, including Vanilla AE, Contractive AE, and Variational AE. The area under the receiver operating characteristic curve (AUC) and the other statistics are used to evaluate the performance of these models. Among the four tested AE models, the proposed multi-task AE model achieves the highest values in AUC (0.964), accuracy (0.821), precision (0.471), and F1 score (0.632), and the lowest value in FPR (0.206). The proposed multi-task AE model using two-dimensional (2D) feature maps can effectively detect anomalies in radiotherapy plans for lung cancer patients. Compared to the other existing AE models, the multi-task AE is more accurate and efficient. The proposed model provides a feasible way to carry out automated anomaly detection of VMAT plans in radiotherapy.

Dynamic Spatio-Temporal Modeling for Enhanced Air Quality Prediction: Implications for Information Management and Public Health Decision Support Systems

Air quality forecasting has significant implications for environmental monitoring, public health, and information management systems. This study proposes three advanced deep learning models: Graph Neural Networks with Dynamic Spatio-Temporal Attention (GNN-DSTA), Multi-Resolution Convolutional Recurrent Neural Networks (MRC-RNN), and Variational Autoencoders with Spatio-Temporal Latent Embeddings (VAE-STLE). These models address the challenges of capturing complex spatio-temporal dependencies in environments with sparse data samples. The GNN-DSTA model introduces a temporal attention mechanism that dynamically captures evolving spatial-temporal dependencies. MRC-RNN combines CNN's spatial pattern recognition with RNN's temporal modeling across multiple spatial resolutions. VAE-STLE provides a probabilistic framework for robust and interpretable forecasting. Experimental results demonstrate significant improvements in prediction accuracy: GNN-DSTA reduces RMSE by 15-20%, MRC-RNN improves accuracy by 12-15%, and VAE-STLE shows a 10-12% improvement with enhanced uncertainty estimation. These models advance AQI predictions through dynamic attention mechanisms, multi-resolution analysis, and probabilistic forecasting. Furthermore, this study explores the implications of these advanced predictions for information management and public health decision support systems. We discuss the integration of real-time data, scalability considerations for large-scale deployments, user interface design for effective communication of predictions, and ethical considerations in using AI-driven models for public health decision-making. The proposed approach not only enhances the accuracy and reliability of AQI predictions but also provides a framework for developing more effective and responsive public health interventions and environmental policies.

A robust detection scheme against selective forwarding attacks in wireless sensor networks under variable harsh environments

Event-driven wireless sensor networks (EWSNs) often operate in harsh environments and are susceptible to selective forwarding attacks, where malicious nodes selectively drop packets. These attacks are difficult to detect due to similarities with normal node behavior under adverse conditions. To address this, we propose a detection scheme combining Variable Autoencoder (VAE) and Gaussian Mixture Model (GMM) with an Autoencoder (AE). The scheme extracts features from the node's single round forwarding rate (SFR), with VAE generating latent variables and GMM clustering them to differentiate behaviors. The AE model, trained on data representing normal behavior, uses reconstruction error to identify malicious nodes. Simulation results show that our scheme improves network throughput and achieves low False Detection Rate (FDR) and Missed Detection Rate (MDR), with both rates as low as 0.5% in normal conditions and below 2% in mobile harsh environments. With a computational complexity of O(n), this method is suitable for resource-constrained environments, demonstrating superior robustness compared to existing approaches.

Uncovering neural substrates across Alzheimer's disease stages using contrastive variational autoencoder.

Alzheimer's disease is the most common major neurocognitive disorder. Although currently, no cure exists, understanding the neurobiological substrate underlying Alzheimer's disease progression will facilitate early diagnosis and treatment, slow disease progression, and improve prognosis. In this study, we aimed to understand the morphological changes underlying Alzheimer's disease progression using structural magnetic resonance imaging data from cognitively normal individuals, individuals with mild cognitive impairment, and Alzheimer's disease via a contrastive variational autoencoder model. We used contrastive variational autoencoder to generate synthetic data to boost the downstream classification performance. Due to the ability to parse out the nonclinical factors such as age and gender, contrastive variational autoencoder facilitated a purer comparison between different Alzheimer's disease stages to identify the pathological changes specific to Alzheimer's disease progression. We showed that brain morphological changes across Alzheimer's disease stages were significantly associated with individuals' neurofilament light chain concentration, a potential biomarker for Alzheimer's disease, highlighting the biological plausibility of our results.

Generating comprehensive lithium battery charging data with generative AI

In optimizing the performance and extending the lifespan of lithium batteries, accurate state prediction is crucial. Traditional regression and classification methods have achieved some success in predicting battery states. However, the effectiveness of these data-driven approaches largely depends on the availability and quality of public datasets. Additionally, generating electrochemical data primarily through battery experiments is a lengthy and costly process, making it extremely difficult to obtain high-quality data. This difficulty, combined with data incompleteness, significantly affects prediction accuracy. To address these challenges, this study introduces End of Life (EOL) and Equivalent Cycle Life (ECL) as supervised conditions for generative AI models. By integrating an embedding layer into the CVAE model, we developed the Refined Conditional Variational Autoencoder (RCVAE). Through preprocessing data into a quasi-video format, coupled with customized training and inference algorithms, the RCVAE generates the required charging data in real time based on the battery’s ECL and EOL. This avoids storing irrelevant information, saving space and resources. RCVAE uses a lightweight architecture, enabling fast generation of necessary voltage, current, temperature, and charging capacity data. This approach provides users with a comprehensive electrochemical dataset, pioneering a new research domain for the artificial synthesis of lithium battery data. Furthermore, based on the detailed synthetic data, various battery state indicators can be calculated, offering new perspectives and possibilities for lithium battery performance prediction.

B-117 Rapid Classification of Cleanliness Grades of Vaginal Discharge through Computational Analysis of SERS Spectra via Variational Auto-Encoder Model And Long Short-Term Memory Networks

Abstract Background Classification of cleanliness grades of vaginal discharge plays a pivotal role in clinical laboratories, serving as indicators for the presence of various vaginal infections such as bacterial vaginosis and candidal vulvovaginitis, etc. The conventional method for assessing vaginal discharge cleanliness involves manual microscopy, a technique susceptible to variations based on the examiner's expertise and subjective judgment, hindering the attainment of swift and accurate diagnoses. Methods This study introduces a novel approach by integrating Surface-Enhanced Raman Spectroscopy (SERS) with a deep learning algorithm for the rapid classification of vaginal discharge cleanliness grades. The proposed classification method combines the Variational Auto-Encoder (VAE) and Long Short-Term Memory (LSTM) to process SERS spectra. The quality of the training data is assessed using the signal-to-noise ratio (SNR) as a standard indicator. Results The application of the VAE-LSTM algorithm significantly enhances classification performance, providing swift and accurate results while reducing the required time. Comparative analyses with various classical machine learning algorithms and evaluation metrics reveal the superior predictive capability and time efficiency of the VAE-LSTM algorithm, demonstrating 100% accuracy and a fitting time of 2 seconds. Blind testing of SERS spectra collected from unknown patients further validates the reliability of the proposed method. Conclusions This study presents a promising and practical approach for the rapid classification of vaginal discharge cleanliness grades. The integration of the SERS technique with the VAE-LSTM algorithm not only ensures accuracy and efficiency in clinical diagnosis but also lays the foundation for advancements in non-invasive diagnostic technologies in gynecological healthcare.

An Emotional Dialogue System Using Conditional Generative Adversarial Networks with a Sequence-to-Sequence Transformer Encoder

Understanding the expression of emotion and generating appropriate responses are key steps toward constructing emotional, conversational agents. In this paper, we propose a framework for single-turn emotional conversation generation, and there are three main components in our model, namely, a sequence-to-sequence model with stacked encoders, a conditional variational autoencoder, and conditional generative adversarial networks. For the sequence-to-sequence model with stacked encoders, we designed a two-layer encoder by combining Transformer with gated recurrent units-based neural networks. Because of the flexibility of the sequence-to-sequence model, we adopted a conditional variational autoencoder in our framework, which uses latent variables to learn a distribution over potential responses and generates diverse responses. Furthermore, we regard a conditional variational autoencoder-based, sequence-to-sequence model as the generative model, and the training of the generative model is assisted by both a content discriminator and an emotion classifier, which assists our model in promoting content information and emotion expression. We use automated evaluation and human evaluation to evaluate our model and baselines on the NTCIR short text conversation task (STC-3) Chinese emotional conversation generation (CECG) Subtask dataset [44], and the experimental results demonstrate that our proposed framework can generate semantically reasonable and emotionally appropriate responses.

Efficient property-oriented design of composite layups via controllable latent features using generative VAE

Fiber-reinforced composites provide substantial tailoring potential, while the extensive parameters and complex coupling mechanisms pose formidable challenges to layup designs. This paper presents an efficient inverse design framework for composite layups utilizing a variational autoencoder (VAE), which is applicable to non-conventional laminates. By leveraging the VAE's exceptional feature extraction and generative capabilities, the decoder rapidly produces layups with desired properties through controllable feature vectors. Based on the stacking characteristics of layups, multi-scale one-dimensional convolutions precisely extract sequence features relevant to mechanical properties and specific manufacturing constraints. A customized loss function is formulated to constrain the latent features, while addressing the non-uniqueness problem for layups with certain mechanical properties. The developed property-oriented VAE can generate 100,000 layups in seconds, achieving an average success rate of 66.9% under comprehensive in-plane and bending stiffness design, and remains effective for 100-ply thick laminate. For comparison, the VAE model outperforms the genetic algorithm and the logic-based method in reinforced panel designs, reducing the retrieval error by 46.4% and 38.1%, respectively. The proposed approach demonstrates flexible and efficient design advantages using generative machine learning models, and is easily extendable to other inverse design scenarios.

Multi-adversarial autoencoders: Stable, faster and self-adaptive representation learning

The variational autoencoder (VAE) and generative adversarial networks (GAN) are two prominent approaches to achieving a probabilistic generative model by way of an autoencoder and a two-player minimax game. While VAEs often suffer from over-simplified posterior approximations, the adversarial autoencoder (AAE) has shown promise by adopting GAN to match the variational posterior to an arbitrary prior through adversarial training. Both VAEs and GANs face significant challenges such as training stability, mode collapse, and difficulty in extracting meaningful latent representations. In this paper, we propose the Multi-adversarial Autoencoder (MAAE), which extends the AAE framework by incorporating multiple discriminators and enabling soft-ensemble feedback. By adaptively regulating the collective feedback from multiple discriminators, MAAE captures a balance between fitting the data distribution and performing accurate inference and accelerates training stability while extracting meaningful and interpretable latent representations. Experimental evaluations on MNIST, CIFAR10, and CelebA datasets demonstrate significant improvements in latent representation, quality of generated samples, log-likelihood, and a pairwise comparison metric, with comparisons to recent methods.