Measles is extremely contagious and is one of the leading causes of vaccine-preventable illness and death in developing countries, claiming more than 100,000 lives each year. Measles was declared eliminated in the US in 2000 due to decades of successful vaccination for the measles. As a result, an increasing number of US healthcare professionals and the public have never seen the disease. Unfortunately, the Measles resurged in the US in 2019 with 1,282 confirmed cases. To assist in diagnosing measles, we collected more than 1300 images of a variety of skin conditions, with which we employed residual deep convolutional neural network to distinguish measles rash from other skin conditions, in an aim to create a phone application in the future. On our image dataset, our model reaches a classification accuracy of 95.2%, sensitivity of 81.7%, and specificity of 97.1%, indicating the model is effective in facilitating an accurate detection of measles to help contain measles outbreaks.

Deep neural networks, when optimized with sufficient data, provide accurate representations of high-dimensional functions; in contrast, function approximation techniques that have predominated in scientific computing do not scale well with dimensionality. As a result, many high-dimensional sampling and approximation problems once thought intractable are being revisited through the lens of machine learning. While the promise of unparalleled accuracy may suggest a renaissance for applications that require parameterizing representations of complex systems, in many applications gathering sufficient data to develop such a representation remains a significant challenge. Here we introduce an approach that combines rare events sampling techniques with neural network optimization to optimize objective functions that are dominated by rare events. We show that importance sampling reduces the asymptotic variance of the solution to a learning problem, suggesting benefits for generalization. We study our algorithm in the context of learning dynamical transition pathways between two states of a system, a problem with applications in statistical physics and implications in machine learning theory. Our numerical experiments demonstrate that we can successfully learn even with the compounding difficulties of high-dimension and rare data.

Generative adversarial networks (GANs) are implicit generative models that can be used for data imputation as an unsupervised learning problem. This works introduces an iterative GAN architecture for data imputation based on the invertibility of the generative imputer. This property is a sufficient condition for the convergence of the proposed GAN architecture. The performance of imputation is demonstrated by applying different imputation algorithms on the traffic speed data from Guangzhou (China). It is shown that our proposed algorithm produces more accurate results compared to those of previous GAN-based imputation architectures.

Open set classification (OSC) tackles the problem of determining whether the data are in-class or out-of-class during inference, when only provided with a set of in-class examples at training time. Traditional OSC methods usually train discriminative or generative models with in-class data, then utilize the pre-trained models to classify test data directly. However, these methods always suffer from embedding confusion problem, i.e., partial out-of-class instances are mixed with in-class ones of similar semantics, making it difficult to classify. To solve this problem, we unify semi-supervised learning to develop a novel OSC algorithm, S2OSC, that incorporates out-of-class instances filtering and model re-training in a transductive manner. In detail, given a pool of newly coming test data, S2OSC firstly filters distinct out-of-class instances using the pre-trained model, and annotates super-class for them. Then, S2OSC trains a holistic classification model by combing in-class and out-of-class labeled data and remaining unlabeled test data in semi-supervised paradigm, which also integrates pre-trained model for knowledge distillation to further separate mixed instances. Despite its simplicity, the experimental results show that S2OSC achieves state-of-the-art performance across a variety of OSC tasks, including 85.4% of F1 on CIFAR-10 with only 300 pseudo-labels. We also demonstrate how S2OSC can be expanded to incremental OSC setting effectively with streaming data.

Data-driven fault diagnosis is complicated by unknown fault classes and limited training data from different fault realizations. In these situations, conventional multi-class classification approaches are not suitable for fault diagnosis. One solution is the use of anomaly classifiers that are trained using only nominal data. Anomaly classifiers can be used to detect when a fault occurs but give little information about its root cause. Hybrid fault diagnosis methods combining physically-based models and available training data have shown promising results to improve fault classification performance and identify unknown fault classes. Residual generation using grey-box recurrent neural networks can be used for anomaly classification where physical insights about the monitored system are incorporated into the design of the machine learning algorithm. In this work, an automated residual design is developed using a bipartite graph representation of the system model to design grey-box recurrent neural networks and evaluated using a real industrial case study. Data from an internal combustion engine test bench is used to illustrate the potentials of combining machine learning and model-based fault diagnosis techniques.

Models are often given in terms of differential equations to represent physical systems. In the presence of uncertainty, accurate prediction of the behavior of these systems using the models requires understanding the effect of uncertainty in the response. In uncertainty quantification, statistics such as mean and variance of the response of these physical systems are sought. To estimate these statistics sampling-based methods like Monte Carlo often require many evaluations of the models' governing equations for multiple realizations of the uncertainty. However, for large complex engineering systems, these methods become computationally burdensome. In structural engineering, often an otherwise linear structure contains spatially local nonlinearities with uncertainty present in them. A standard nonlinear solver for them with sampling-based methods for uncertainty quantification incurs significant computational cost for estimating the statistics of the response. To ease this computational burden of uncertainty quantification of large-scale locally nonlinear dynamical systems, a method is proposed herein, which decomposes the response into two parts -- response of a nominal linear system and a corrective term. This corrective term is the response from a pseudoforce that contains the nonlinearity and uncertainty information. In this paper, neural network, a recently popular tool for universal function approximation in the scientific machine learning community due to the advancement of computational capability as well as the availability of open-sourced packages like PyTorch and TensorFlow is used to estimate the pseudoforce. Since only the nonlinear and uncertain pseudoforce is modeled using the neural networks the same network can be used to predict a different response of the system and hence no new network is required to train if the statistic of a different response is sought.

We propose PiNet, a generalised differentiable attention-based pooling mechanism for utilising graph convolution operations for graph level classification. We demonstrate high sample efficiency and superior performance over other graph neural networks in distinguishing isomorphic graph classes, as well as competitive results with state of the art methods on standard chemo-informatics datasets.

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the distributed nature of FL gives rise to new threats caused by potentially malicious participants. In this paper, we study targeted data poisoning attacks against FL systems in which a malicious subset of the participants aim to poison the global model by sending model updates derived from mislabeled data. We first demonstrate that such data poisoning attacks can cause substantial drops in classification accuracy and recall, even with a small percentage of malicious participants. We additionally show that the attacks can be targeted, i.e., they have a large negative impact only on classes that are under attack. We also study attack longevity in early/late round training, the impact of malicious participant availability, and the relationships between the two. Finally, we propose a defense strategy that can help identify malicious participants in FL to circumvent poisoning attacks, and demonstrate its effectiveness.

Automatic Chest Radiograph X-ray (CXR) interpretation by machines is an important research topic of Artificial Intelligence. As part of my journey through the California Science Fair, I have developed an algorithm that can detect pneumonia from a CXR image to compensate for human fallibility. My algorithm, PneumoXttention, is an ensemble of two 13 layer convolutional neural network trained on the RSNA dataset, a dataset provided by the Radiological Society of North America, containing 26,684 frontal X-ray images split into the categories of pneumonia and no pneumonia. The dataset was annotated by many professional radiologists in North America. It achieved an impressive F1 score, 0.82, on the test set (20% random split of RSNA dataset) and completely compensated Human Radiologists on a random set of 25 test images drawn from RSNA and NIH. I don't have a direct comparison but Stanford's Chexnet has a F1 score of 0.435 on the NIH dataset for category Pneumonia.

With the rise of computing power and advancements in algorithms, there's something amusing and interesting happening in the field of Artificial Intelligence and Machine Learning every day that it becomes difficult to keep up with the pace. Natural Language Processing is gaining new momentum as transformer models like BERT, GPT, RoBERT, XLNET and others are making it possible to create more advanced chatbots which can closely replicate a human and are easy to deploy and maintain along with huge cost savings. To be updated with the recent inventions and advancements, here's a list of top AI blogs I personally follow: Google has few of the best talents on the planet working for its Google research, Google Brain and the overall Google team. They have been successful in finding solutions to some of the most challenging computer science problems and are also the developers of ML platforms like Tensorflow. The Google research blog has all the articles, papers and other relevant content explaining what Google has been able to achieve.