ALBERT

Description: The two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) for solving partially observable Markov decision processes (POMDP) problems. Reinforcement Learning (RL) is an approach to simulate the human’s natural learning process, whose key is to let the agent learn by interacting with the stochastic environment. The fact that the agent has limited access to the information of the environment enables AI to be applied efficiently in most fields that require self-learning. It’s essential to have an organized investigation—we can make good comparisons and choose the best structures or algorithms when applying DRL in various applications. The first part of the overview introduces Markov Decision Processes (MDP) problems and Reinforcement Learning and applications of DRL for solving POMDP problems in games, robotics, and natural language processing. In part two, we continue to introduce applications in transportation, industries, communications and networking, etc. and discuss the limitations of DRL.

Description: This review article provides a deep insight into the Brain–Computer Interface (BCI) and the application of Machine Learning (ML) technology in BCIs. It investigates the various types of research undertaken in this realm and discusses the role played by ML in performing different BCI tasks. It also reviews the ML methods used for mental state detection, mental task categorization, emotion classification, electroencephalogram (EEG) signal classification, event-related potential (ERP) signal classification, motor imagery categorization, and limb movement classification. This work explores the various methods employed in BCI mechanisms for feature extraction, selection, and classification and provides a comparative study of reviewed methods. This paper assists the readers to gain information regarding the developments made in BCI and ML domains and future improvements needed for improving and designing better BCI applications.

Description: In this paper, we present the potential of Explainable Artificial Intelligence methods for decision support in medical image analysis scenarios. Using three types of explainable methods applied to the same medical image data set, we aimed to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). In vivo gastral images obtained by a video capsule endoscopy (VCE) were the subject of visual explanations, with the goal of increasing health professionals’ trust in black-box predictions. We implemented two post hoc interpretable machine learning methods, called Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), and an alternative explanation approach, the Contextual Importance and Utility (CIU) method. The produced explanations were assessed by human evaluation. We conducted three user studies based on explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in a web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n = 20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We found that, as hypothesized, the CIU-explainable method performed better than both LIME and SHAP methods in terms of improving support for human decision-making and being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decision-making between various explanation support settings. In line with that, we present three potential explainable methods that, with future improvements in implementation, can be generalized to different medical data sets and can provide effective decision support to medical experts.

Description: Predictive analytics using artificial intelligence is a useful tool in cancer research. A multilayer perceptron neural network used gene expression data to predict the lymphoma subtypes of 290 cases of non-Hodgkin lymphoma (GSE132929). The input layer included both the whole array of 20,863 genes and a cancer transcriptome panel of 1769 genes. The output layer was lymphoma subtypes, including follicular lymphoma, mantle cell lymphoma, diffuse large B-cell lymphoma, Burkitt lymphoma, and marginal zone lymphoma. The neural networks successfully classified the cases consistent with the lymphoma subtypes, with an area under the curve (AUC) that ranged from 0.87 to 0.99. The most relevant predictive genes were LCE2B, KNG1, IGHV7_81, TG, C6, FGB, ZNF750, CTSV, INGX, and COL4A6 for the whole set; and ARG1, MAGEA3, AKT2, IL1B, S100A7A, CLEC5A, WIF1, TREM1, DEFB1, and GAGE1 for the cancer panel. The characteristic predictive genes for each lymphoma subtypes were also identified with high accuracy (AUC = 0.95, incorrect predictions = 6.2%). Finally, the topmost relevant 30 genes of the whole set, which belonged to apoptosis, cell proliferation, metabolism, and antigen presentation pathways, not only predicted the lymphoma subtypes but also the overall survival of diffuse large B-cell lymphoma (series GSE10846, n = 414 cases), and most relevant cancer subtypes of The Cancer Genome Atlas (TCGA) consortium including carcinomas of breast, colorectal, lung, prostate, and gastric, melanoma, etc. (7441 cases). In conclusion, neural networks predicted the non-Hodgkin lymphoma subtypes with high accuracy, and the highlighted genes also predicted the survival of a pan-cancer series.

Description: Clustering is a widely used unsupervised learning technique across data mining and machine learning applications and finds frequent use in diverse fields ranging from astronomy, medical imaging, search and optimization, geology, geophysics, and sentiment analysis, to name a few. It is therefore important to verify the effectiveness of the clustering algorithm in question and to make reasonably strong arguments for the acceptance of the end results generated by the validity indices that measure the compactness and separability of clusters. This work aims to explore the successes and limitations of two popular clustering mechanisms by comparing their performance over publicly available benchmarking data sets that capture a variety of data point distributions as well as the number of attributes, especially from a computational point of view by incorporating techniques that alleviate some of the issues that plague these algorithms. Sensitivity to initialization conditions and stagnation to local minima are explored. Further, an implementation of a feedforward neural network utilizing a fully connected topology in particle swarm optimization is introduced. This serves to be a guided random search technique for the neural network weight optimization. The algorithms utilized here are studied and compared, from which their applications are explored. The study aims to provide a handy reference for practitioners to both learn about and verify benchmarking results on commonly used real-world data sets from both a supervised and unsupervised point of view before application in more tailored, complex problems.

Description: Due to impressive performance, deep neural networks for object detection in images have become a prevalent choice. Given the complexity of the neural network models used, users of these algorithms are typically given no hint as to how the objects were found. It remains, for example, unclear whether an object is detected based on what it looks like or based on the context in which it is located. We have developed an algorithm, Surrogate Object Detection Explainer (SODEx), that can explain any object detection algorithm using any classification explainer. We evaluate SODEx qualitatively and quantitatively by detecting objects in the COCO dataset with YOLOv4 and explaining these detections with LIME. This empirical evaluation does not only demonstrate the value of explainable object detection, it also provides valuable insights into how YOLOv4 detects objects.

Description: Machine learning is an established and frequently used technique in industry and academia, but a standard process model to improve success and efficiency of machine learning applications is still missing. Project organizations and machine learning practitioners face manifold challenges and risks when developing machine learning applications and have a need for guidance to meet business expectations. This paper therefore proposes a process model for the development of machine learning applications, covering six phases from defining the scope to maintaining the deployed machine learning application. Business and data understanding are executed simultaneously in the first phase, as both have considerable impact on the feasibility of the project. The next phases are comprised of data preparation, modeling, evaluation, and deployment. Special focus is applied to the last phase, as a model running in changing real-time environments requires close monitoring and maintenance to reduce the risk of performance degradation over time. With each task of the process, this work proposes quality assurance methodology that is suitable to address challenges in machine learning development that are identified in the form of risks. The methodology is drawn from practical experience and scientific literature, and has proven to be general and stable. The process model expands on CRISP-DM, a data mining process model that enjoys strong industry support, but fails to address machine learning specific tasks. The presented work proposes an industry- and application-neutral process model tailored for machine learning applications with a focus on technical tasks for quality assurance.

Description: The diffused practice of pre-training Convolutional Neural Networks (CNNs) on large natural image datasets such as ImageNet causes the automatic learning of invariance to object scale variations. This, however, can be detrimental in medical imaging, where pixel spacing has a known physical correspondence and size is crucial to the diagnosis, for example, the size of lesions, tumors or cell nuclei. In this paper, we use deep learning interpretability to identify at what intermediate layers such invariance is learned. We train and evaluate different regression models on the PASCAL-VOC (Pattern Analysis, Statistical modeling and ComputAtional Learning-Visual Object Classes) annotated data to (i) separate the effects of the closely related yet different notions of image size and object scale, (ii) quantify the presence of scale information in the CNN in terms of the layer-wise correlation between input scale and feature maps in InceptionV3 and ResNet50, and (iii) develop a pruning strategy that reduces the invariance to object scale of the learned features. Results indicate that scale information peaks at central CNN layers and drops close to the softmax, where the invariance is reached. Our pruning strategy uses this to obtain features that preserve scale information. We show that the pruning significantly improves the performance on medical tasks where scale is a relevant factor, for example for the regression of breast histology image magnification. These results show that the presence of scale information at intermediate layers legitimates transfer learning in applications that require scale covariance rather than invariance and that the performance on these tasks can be improved by pruning off the layers where the invariance is learned. All experiments are performed on publicly available data and the code is available on GitHub.

Description: A common privacy issue in traditional machine learning is that data needs to be disclosed for the training procedures. In situations with highly sensitive data such as healthcare records, accessing this information is challenging and often prohibited. Luckily, privacy-preserving technologies have been developed to overcome this hurdle by distributing the computation of the training and ensuring the data privacy to their owners. The distribution of the computation to multiple participating entities introduces new privacy complications and risks. In this paper, we present a privacy-preserving decentralised workflow that facilitates trusted federated learning among participants. Our proof-of-concept defines a trust framework instantiated using decentralised identity technologies being developed under Hyperledger projects Aries/Indy/Ursa. Only entities in possession of Verifiable Credentials issued from the appropriate authorities are able to establish secure, authenticated communication channels authorised to participate in a federated learning workflow related to mental health data.

Description: Neural networks present characteristics where the results are strongly dependent on the training data, the weight initialisation, and the hyperparameters chosen. The determination of the distribution of a statistical estimator, as the Mean Squared Error (MSE) or the accuracy, is fundamental to evaluate the performance of a neural network model (NNM). For many machine learning models, as linear regression, it is possible to analytically obtain information as variance or confidence intervals on the results. Neural networks present the difficulty of not being analytically tractable due to their complexity. Therefore, it is impossible to easily estimate distributions of statistical estimators. When estimating the global performance of an NNM by estimating the MSE in a regression problem, for example, it is important to know the variance of the MSE. Bootstrap is one of the most important resampling techniques to estimate averages and variances, between other properties, of statistical estimators. In this tutorial, the application of resampling techniques (including bootstrap) to the evaluation of neural networks’ performance is explained from both a theoretical and practical point of view. The pseudo-code of the algorithms is provided to facilitate their implementation. Computational aspects, as the training time, are discussed, since resampling techniques always require simulations to be run many thousands of times and, therefore, are computationally intensive. A specific version of the bootstrap algorithm is presented that allows the estimation of the distribution of a statistical estimator when dealing with an NNM in a computationally effective way. Finally, algorithms are compared on both synthetically generated and real data to demonstrate their performance.