HUAWEI CLOUD's Enterprise Intelligence (EI) has achieved strong results in numerous industry competitions and evaluations. HUAWEI CLOUD has invested heavily in basic research AI in three domains: computer vision, speech and semantics, and decision optimization. To help AI empower all industries, the ModelArts enabling platform supports plug-and-play deployment of HUAWEI CLOUD's research results in areas such as automatic machine learning, small sample learning, federated learning, and pre-training models. In the area of perception, HUAWEI CLOUD continues to be an industry-leader in ImageNet large-scale image classification, WebVision large-scale network image classification, MS-COCO two-dimensional object detection, nuScenes three-dimensional object detection, and visual pre-training model verification, including downstream classification, detection, and segmentation. Perception models driven by ModelArts have been widely used in sectors such as medical image analysis, oil and gas exploration, and fault detection in manufacturing. In cognition, HUAWEI CLOUD integrates industry data based on its expertise in semantic analysis and knowledge graphs.

Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper shows that for a wide range of classifiers, globally referred to as decision graphs, and which include decision trees and binary decision diagrams, but also their multi-valued variants, there exist polynomial-time algorithms for computing one PI-explanation. In addition, the paper also proposes a polynomial-time algorithm for computing one contrastive explanation. These novel algorithms build on explanation graphs (XpG's). XpG's denote a graph representation that enables both theoretical and practically efficient computation of explanations for decision graphs. Furthermore, the paper pro- poses a practically efficient solution for the enumeration of explanations, and studies the complexity of deciding whether a given feature is included in some explanation. For the concrete case of decision trees, the paper shows that the set of all contrastive explanations can be enumerated in polynomial time. Finally, the experimental results validate the practical applicability of the algorithms proposed in the paper on a wide range of publicly available benchmarks.

Causal models are notoriously difficult to validate because they make untestable assumptions regarding confounding. New scientific experiments offer the possibility of evaluating causal models using prediction performance. Prediction performance measures are typically robust to violations in causal assumptions. However prediction performance does depend on the selection of training and test sets. In particular biased training sets can lead to optimistic assessments of model performance. In this work, we revisit the prediction performance of several recently proposed causal models tested on a genetic perturbation data set of Kemmeren [Kemmeren et al., 2014]. We find that sample selection bias is likely a key driver of model performance. We propose using a less-biased evaluation set for assessing prediction performance on Kemmeren and compare models on this new set. In this setting, the causal model tested have similar performance to standard association based estimators such as Lasso. Finally we compare the performance of causal estimators in simulation studies which reproduce the Kemmeren structure of genetic knockout experiments but without any sample selection bias. These results provide an improved understanding of the performance of several causal models and offer guidance on how future studies should use Kemmeren.

OBJECTIVES: Misdiagnosis of acute and chronic otitis media in children can result in significant consequences from either undertreatment or overtreatment. Our objective was to develop and train an artificial intelligence algorithm to accurately predict the presence of middle ear effusion in pediatric patients presenting to the operating room for myringotomy and tube placement. METHODS: We trained a neural network to classify images as “ normal” (no effusion) or “abnormal” (effusion present) using tympanic membrane images from children taken to the operating room with the intent of performing myringotomy and possible tube placement for recurrent acute otitis media or otitis media with effusion. Model performance was tested on held-out cases and fivefold cross-validation. RESULTS: The mean training time for the neural network model was 76.0 (SD ± 0.01) seconds. Our model approach achieved a mean image classification accuracy of 83.8% (95% confidence interval [CI]: 82.7–84.8). In support of this classification accuracy, the model produced an area under the receiver operating characteristic curve performance of 0.93 (95% CI: 0.91–0.94) and F1-score of 0.80 (95% CI: 0.77–0.82). CONCLUSIONS: Artificial intelligence–assisted diagnosis of acute or chronic otitis media in children may generate value for patients, families, and the health care system by improving point-of-care diagnostic accuracy. With a small training data set composed of intraoperative images obtained at time of tympanostomy tube insertion, our neural network was accurate in predicting the presence of a middle ear effusion in pediatric ear cases. This diagnostic accuracy performance is considerably higher than human-expert otoscopy-based diagnostic performance reported in previous studies.

Background: Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate. We use 64 two-dimensional speckle tracking echocardiography (2D-STE) features and seven clinical features to predict whether one has CHD. Methods: We develop a machine learning approach that integrates a number of popular classification methods together by model stacking, and generalize the traditional stacking method to a two-step stacking method to improve the diagnostic performance. Results: By borrowing strengths from multiple classification models through the proposed method, we improve the CHD classification accuracy from around 70% to 87.7% on the testing set. The sensitivity of the proposed method is 0.903 and the specificity is 0.843, with an AUC of 0.904, which is significantly higher than those of the individual classification models. Conclusions: Our work lays a foundation for the deployment of speckle tracking echocardiography-based screening tools for coronary heart disease.

Research in Cognitive Science suggests that humans understand and represent knowledge of the world through causal relationships. In addition to observations, they can rely on experimenting and counterfactual reasoning -- i.e. referring to an alternative course of events -- to identify causal relations and explain atypical situations. Different instances of control systems, such as smart homes, would benefit from having a similar causal model, as it would help the user understand the logic of the system and better react when needed. However, while data-driven methods achieve high levels of correlation detection, they mainly fall short of finding causal relations, notably being limited to observations only. Notably, they struggle to identify the cause from the effect when detecting a correlation between two variables. This paper introduces a new way to learn causal models from a mixture of experiments on the environment and observational data. The core of our method is the use of selected interventions, especially our learning takes into account the variables where it is impossible to intervene, unlike other approaches. The causal model we obtain is then used to generate Causal Bayesian Networks, which can be later used to perform diagnostic and predictive inference. We use our method on a smart home simulation, a use case where knowing causal relations pave the way towards explainable systems. Our algorithm succeeds in generating a Causal Bayesian Network close to the simulation's ground truth causal interactions, showing encouraging prospects for application in real-life systems.

Reconfiguration aims at recovering a system from a fault by automatically adapting the system configuration, such that the system goal can be reached again. Classical approaches typically use a set of pre-defined faults for which corresponding recovery actions are defined manually. This is not possible for modern hybrid systems which are characterized by frequent changes. Instead, AI-based approaches are needed which leverage on a model of the non-faulty system and which search for a set of reconfiguration operations which will establish a valid behavior again. This work presents a novel algorithm which solves three main challenges: (i) Only a model of the non-faulty system is needed, i.e. the faulty behavior does not need to be modeled. (ii) It discretizes and reduces the search space which originally is too large -- mainly due to the high number of continuous system variables and control signals. (iii) It uses a SAT solver for propositional logic for two purposes: First, it defines the binary concept of validity. Second, it implements the search itself -- sacrificing the optimal solution for a quick identification of an arbitrary solution. It is shown that the approach is able to reconfigure faults on simulated process engineering systems.

I want to expand this work into a series of µ-tutorial videos. If you're interested, please subscribe to my newsletter to stay in touch. It is not hard to be under an impression that the world is all about neural networks these days when it comes to making models. Many teams seem to brag about super-cool architectures as if getting enough quality data was straightforward, GPU racks were open 24/7 (for free), and their customer's patience was set to infinity. In this article, we will present one of the most basic machine-learning algorithms known as a Decision Tree.

Paul De Sousa, head of life sciences at Massive Analytic and former researcher at Edinburgh University, writes about a study using artificial precognition AI to analyse results of protein biomarker tests associated with Alzheimer's disease progression. Accounting for over 30 million Disability Adjusted Life Years worldwide, Alzheimer's disease (AD) is a global societal challenge and a threat to healthcare systems around the world. A long history of failures of AD drug trials has highlighted the need for early detection and diagnosis to support patients and clinicians to implement the best life adjustments or medical interventions to alter the course of the disease and personalise the care of those at risk. Biomarkers are measurable indicators of the biological conditions of health, on which disease prognosis and diagnosis is founded. In AD there are a range of diagnostic procedures to detect these biomarkers including testing Cerebrospinal fluid (CSF) and PET scans for markers of amyloid-β and tau that can accurately detect AD pathology, but their cost and invasive nature preclude the broad accessibility required for early detection.

We give a quasipolynomial-time algorithm for learning stochastic decision trees that is optimally resilient to adversarial noise. Given an $\eta$-corrupted set of uniform random samples labeled by a size-$s$ stochastic decision tree, our algorithm runs in time $n^{O(\log(s/\varepsilon)/\varepsilon^2)}$ and returns a hypothesis with error within an additive $2\eta + \varepsilon$ of the Bayes optimal. An additive $2\eta$ is the information-theoretic minimum. Previously no non-trivial algorithm with a guarantee of $O(\eta) + \varepsilon$ was known, even for weaker noise models. Our algorithm is furthermore proper, returning a hypothesis that is itself a decision tree; previously no such algorithm was known even in the noiseless setting.