The Department of Defense Joint Artificial Intelligence Center (JAIC) is continuing to operationalize Responsible Artificial Intelligence with the announcement of a pilot of a procurement review process that will ensure AI acquired by the JAIC is aligned with DoD's AI Ethics Principles. The DoD AI Ethics Principles, along with operational commitments, are outlined in the recently issued memorandum on implementing responsible AI. Responsible AI Institute will support the pilot. "The development of a tactical responsible AI procurement process is essential for creating the necessary safeguards aligned with our AI Ethics Principles and further implement against the responsible AI tenants set forth by the Deputy Secretary of Defense," says Alka Patel, Chief of Responsible AI at the JAIC. The Responsible AI Procurement pilot is part of a holistic approach that focuses not only on the technology but also on organizational operating structures and culture to advance Responsible AI within the DoD.

Using artificial intelligence (AI), researchers from UT Southwestern have developed a way to accurately predict which skin cancers are highly metastatic. The findings, published as the July cover article of Cell Systems, show the potential for AI-based tools to revolutionize pathology for cancer and a variety of other diseases. "We now have a general framework that allows us to take tissue samples and predict mechanisms inside cells that drive disease, mechanisms that are currently inaccessible in any other way," said study leader Gaudenz Danuser, Ph.D., Professor and Chair of the Lyda Hill Department of Bioinformatics at UTSW. AI technology has significantly advanced over the past several years, Dr. Danuser explained, with deep learning-based methods able to distinguish minute differences in images that are essentially invisible to the human eye. Researchers have proposed using this latent information to look for differences in disease characteristics that could offer insight on prognoses or guide treatments.

We design a multiscopic vision system that utilizes a low-cost monocular RGB camera to acquire accurate depth estimation. Unlike multi-view stereo with images captured at unconstrained camera poses, the proposed system controls the motion of a camera to capture a sequence of images in horizontally or vertically aligned positions with the same parallax. In this system, we propose a new heuristic method and a robust learning-based method to fuse multiple cost volumes between the reference image and its surrounding images. To obtain training data, we build a synthetic dataset with multiscopic images. The experiments on the real-world Middlebury dataset and real robot demonstration show that our multiscopic vision system outperforms traditional two-frame stereo matching methods in depth estimation. Our code and dataset are available at https://sites.google.com/view/multiscopic.

Extreme Learning Machine is a powerful classification method very competitive existing classification methods. It is extremely fast at training. Nevertheless, it cannot perform face verification tasks properly because face verification tasks require comparison of facial images of two individuals at the same time and decide whether the two faces identify the same person. The structure of Extreme Leaning Machine was not designed to feed two input data streams simultaneously, thus, in 2-input scenarios Extreme Learning Machine methods are normally applied using concatenated inputs. However, this setup consumes two times more computational resources and it is not optimized for recognition tasks where learning a separable distance metric is critical. For these reasons, we propose and develop a Siamese Extreme Learning Machine (SELM). SELM was designed to be fed with two data streams in parallel simultaneously. It utilizes a dual-stream Siamese condition in the extra Siamese layer to transform the data before passing it along to the hidden layer. Moreover, we propose a Gender-Ethnicity-Dependent triplet feature exclusively trained on a variety of specific demographic groups. This feature enables learning and extracting of useful facial features of each group. Experiments were conducted to evaluate and compare the performances of SELM, Extreme Learning Machine, and DCNN. The experimental results showed that the proposed feature was able to perform correct classification at 97.87% accuracy and 99.45% AUC. They also showed that using SELM in conjunction with the proposed feature provided 98.31% accuracy and 99.72% AUC. They outperformed the well-known DCNN and Extreme Leaning Machine methods by a wide margin.

Annotating the driving scenario trajectories based only on explicit rules (i.e., knowledge-based methods) can be subject to errors, such as false positive/negative classification of scenarios that lie on the border of two scenario classes, missing unknown scenario classes, and also anomalies. On the other side, verifying the labels by the annotators is not cost-efficient. For this purpose, active learning (AL) could potentially improve the annotation procedure by inclusion of an annotator/expert in an efficient way. In this study, we develop an active learning framework to annotate driving trajectory time-series data. At the first step, we compute an embedding of the time-series trajectories into a latent space in order to extract the temporal nature. For this purpose, we study three different latent space representations: multivariate Time Series t-Distributed Stochastic Neighbor Embedding (mTSNE), Recurrent Auto-Encoder (RAE) and Variational Recurrent Auto-Encoder (VRAE). We then apply different active learning paradigms with different classification models to the embedded data. In particular, we study the two classifiers Neural Network (NN) and Support Vector Machines (SVM), with three active learning query strategies (i.e., entropy, margin and random). In the following, we explore the possibilities of the framework to discover unknown classes and demonstrate how it can be used to identify the out-of-class trajectories.

Deep neural network (DNN) classifiers are powerful tools that drive a broad spectrum of important applications, from image recognition to autonomous vehicles. Unfortunately, DNNs are known to be vulnerable to adversarial attacks that affect virtually all state-of-the-art models. These attacks make small imperceptible modifications to inputs that are sufficient to induce the DNNs to produce the wrong classification. In this paper we propose a novel, lightweight adversarial correction and/or detection mechanism for image classifiers that relies on undervolting (running a chip at a voltage that is slightly below its safe margin). We propose using controlled undervolting of the chip running the inference process in order to introduce a limited number of compute errors. We show that these errors disrupt the adversarial input in a way that can be used either to correct the classification or detect the input as adversarial. We evaluate the proposed solution in an FPGA design and through software simulation. We evaluate 10 attacks and show average detection rates of 77% and 90% on two popular DNNs.

The aortic vessel tree is composed of the aorta and its branching arteries, and plays a key role in supplying the whole body with blood. Aortic diseases, like aneurysms or dissections, can lead to an aortic rupture, whose treatment with open surgery is highly risky. Therefore, patients commonly undergo drug treatment under constant monitoring, which requires regular inspections of the vessels through imaging. The standard imaging modality for diagnosis and monitoring is computed tomography (CT), which can provide a detailed picture of the aorta and its branching vessels if combined with a contrast agent, resulting in a CT angiography (CTA). Optimally, the whole aortic vessel tree geometry from consecutive CTAs, are overlaid and compared. This allows to not only detect changes in the aorta, but also more peripheral vessel tree changes, caused by the primary pathology or newly developed. When performed manually, this reconstruction requires slice by slice contouring, which could easily take a whole day for a single aortic vessel tree and, hence, is not feasible in clinical practice. Automatic or semi-automatic vessel tree segmentation algorithms, on the other hand, can complete this task in a fraction of the manual execution time and run in parallel to the clinical routine of the clinicians. In this paper, we systematically review computing techniques for the automatic and semi-automatic segmentation of the aortic vessel tree. The review concludes with an in-depth discussion on how close these state-of-the-art approaches are to an application in clinical practice and how active this research field is, taking into account the number of publications, datasets and challenges.

We investigate the functioning of a classifying biological neural network from the perspective of statistical learning theory, modelled, in a simplified setting, as a continuous-time stochastic recurrent neural network (RNN) with identity activation function. In the purely stochastic (robust) regime, we give a generalisation error bound that holds with high probability, thus showing that the empirical risk minimiser is the best-in-class hypothesis. We show that RNNs retain a partial signature of the paths they are fed as the unique information exploited for training and classification tasks. We argue that these RNNs are easy to train and robust and back these observations with numerical experiments on both synthetic and real data.

An increasing number and diversity of services are available, which result in significant challenges to effective reuse service during requirement satisfaction. There have been many service bundle recommendation studies and achieved remarkable results. However, there is still plenty of room for improvement in the performance of these methods. The fundamental problem with these studies is that they ignore the evolution of services over time and the representation gap between services and requirements. In this paper, we propose a dynamic representation learning and aligning based model called DySR to tackle these issues. DySR eliminates the representation gap between services and requirements by learning a transformation function and obtains service representations in an evolving social environment through dynamic graph representation learning. Extensive experiments conducted on a real-world dataset from ProgrammableWeb show that DySR outperforms existing state-of-the-art methods in commonly used evaluation metrics, improving $F1@5$ from $36.1\%$ to $69.3\%$.

The research on human emotion under multimedia stimulation based on physiological signals is an emerging field, and important progress has been achieved for emotion recognition based on multi-modal signals. However, it is challenging to make full use of the complementarity among spatial-spectral-temporal domain features for emotion recognition, as well as model the heterogeneity and correlation among multi-modal signals. In this paper, we propose a novel two-stream heterogeneous graph recurrent neural network, named HetEmotionNet, fusing multi-modal physiological signals for emotion recognition. Specifically, HetEmotionNet consists of the spatial-temporal stream and the spatial-spectral stream, which can fuse spatial-spectral-temporal domain features in a unified framework. Each stream is composed of the graph transformer network for modeling the heterogeneity, the graph convolutional network for modeling the correlation, and the gated recurrent unit for capturing the temporal domain or spectral domain dependency. Extensive experiments on two real-world datasets demonstrate that our proposed model achieves better performance than state-of-the-art baselines.