The objective optimization of medical imaging systems requires full characterization of all sources of randomness in the measured data, which includes the variability within the ensemble of objects to-be-imaged. This can be accomplished by establishing a stochastic object model (SOM) that describes the variability in the class of objects to-be-imaged. Generative adversarial networks (GANs) can be potentially useful to establish SOMs because they hold great promise to learn generative models that describe the variability within an ensemble of training data. However, because medical imaging systems record imaging measurements that are noisy and indirect representations of object properties, GANs cannot be directly applied to establish stochastic models of objects to-be-imaged. To address this issue, an augmented GAN architecture named AmbientGAN was developed to establish SOMs from noisy and indirect measurement data. However, because the adversarial training can be unstable, the applicability of the AmbientGAN can be potentially limited. In this work, we propose a novel training strategy---Progressive Growing of AmbientGANs (ProAGAN)---to stabilize the training of AmbientGANs for establishing SOMs from noisy and indirect imaging measurements. An idealized magnetic resonance (MR) imaging system and clinical MR brain images are considered. The proposed methodology is evaluated by comparing signal detection performance computed by use of ProAGAN-generated synthetic images and images that depict the true object properties.

In the context of some machine learning applications, obtaining data instances is a relatively easy process but labeling them could become quite expensive or tedious. Such scenarios lead to datasets with few labeled instances and a larger number of unlabeled ones. Semi-supervised classification techniques combine labeled and unlabeled data during the learning phase in order to increase classifier's generalization capability. Regrettably, most successful semi-supervised classifiers do not allow explaining their outcome, thus behaving like black boxes. However, there is an increasing number of problem domains in which experts demand a clear understanding of the decision process. In this paper, we report on an extended experimental study presenting an interpretable self-labeling grey-box classifier that uses a black box to estimate the missing class labels and a white box to make the final predictions. Two different approaches for amending the self-labeling process are explored: a first one based on the confidence of the black box and the latter one based on measures from Rough Set Theory. The results of the extended experimental study support the interpretability by means of transparency and simplicity of our classifier, while attaining superior prediction rates when compared with state-of-the-art self-labeling classifiers reported in the literature.

The ingenious use of quantum effects has led to a significant number of quantum machine learning algorithms that offer computational speedups [1, 2]. While awaiting the demonstration of these quantum algorithms on full-fledge quantum computers equipped with quantum error correction, quantum computing has transitioned from theoretical ideas to the noisy intermediate-scale quantum (NISQ) technology era [3]. Hybrid quantum-classical algorithms using short-depth circuits are particularly suitable for implementation on NISQ devices. Many notable experimental demonstrations of NISQ devices employ hybrid algorithms for data classification [4] and quantum chemistry [5]. An ongoing quest is to find interesting applications on quantum computers with increasingly lower noise profile but not reaching a low enough threshold to enable continuous quantum error correction. Here we propose a hybrid quantum-classical algorithm that utilizes dissipative quantum dynamics for temporal information processing on gate-model NISQ quantum processors. Our approach exploits dissipative quantum systems as universal approximators for nonlinear maps with short-term or fading memory, important in a broad class of real-world problems including spoken digit recognition [6], neural modeling [7] and machine learning tasks (e.g., speech processing and natural language processing) [8, 9]. This is a quantum analogue of the universal function approximation property neural networks enjoy [10], but for nonlinear mappings from sequential input to sequential output data [11-13].

DVERSARIAL attacks on neural networks pose a serious threat to safety-critical systems that rely on the high accuracies of these neural networks. The imperceptibility of additive evasion attacks makes it difficult to even detect their existence. Recent work has attempted to tackle this issue by designing defenses against such attacks, mostly focusing on a scenario where the assumption is that the attacker has significant knowledge of the victim classifier, and hence will design an attack to optimally destroy the accuracy of that particular classifier. However, there is no guarantee that the attacker will choose to do so. Furthermore, adversarial examples transfer across classifiers, and an adversary could take advantage of this property by crafting an attack based on a different classifier. The attacker would do this when having only partial knowledge about the victim classifier, or when attempting to confuse the defender on purpose. Alternatively, another scenario is that the attacker is limited in computational resources, and may be trying to attack multiple classifiers at once. This is why they would tailor the attack to only one classifier, and use that to attack all classifiers. R. Mahfuz, R. Sahay, and A. El Gamal are with the Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA.

We propose a novel neural network architecture, named the Global Workspace Network (GWN), that addresses the challenge of dynamic uncertainties in multimodal data fusion. The GWN is inspired by the well-established Global Workspace Theory from cognitive science. We implement it as a model of attention, between multiple modalities, that evolves through time. The GWN achieved F1 score of 0.92, averaged over two classes, for the discrimination between patient and healthy participants, based on the multimodal EmoPain dataset captured from people with chronic pain and healthy people performing different types of exercise movements in unconstrained settings. In this task, the GWN significantly outperformed a vanilla architecture. It additionally outperformed the vanilla model in further classification of three pain levels for a patient (average F1 score = 0.75) based on the EmoPain dataset. We further provide extensive analysis of the behaviour of GWN and its ability to deal with uncertainty in multimodal data.

Gradient boosted decision trees (GBDT) is the leading algorithm for many commercial and academic data applications. We give a deep analysis of this algorithm, especially the histogram technique, which is a basis for the regulized distribution with compact support. We present three new modifications. 1) Share memory technique to reduce memory usage. In many cases, it only need the data source itself and no extra memory. 2) Implicit merging for "merge overflow problem"."merge overflow" means that merge some small datasets to huge datasets, which are too huge to be solved. By implicit merging, we just need the original small datasets to train the GBDT model. 3) Adaptive resize algorithm of histogram bins to improve accuracy. Experiments on two large Kaggle competitions verified our methods. They use much less memory than LightGBM and have higher accuracy. We have implemented these algorithms in an open-source package LiteMORT. The source codes are available at https://github.com/closest-git/LiteMORT

Aggregate network properties such as cluster cohesion and the number of bridge nodes can be used to glean insights about a network's community structure, spread of influence and the resilience of the network to faults. Efficiently computing network properties when the network is fully observed has received significant attention (Wasserman and Faust 1994; Cook and Holder 2006), however the problem of computing aggregate network properties when there is missing data attributes has received little attention. Computing these properties for networks with missing attributes involves performing inference over the network. Statistical relational learning (SRL) and graph neural networks (GNNs) are two classes of machine learning approaches well suited for inferring missing attributes in a graph. In this paper, we study the effectiveness of these approaches in estimating aggregate properties on networks with missing attributes. We compare two SRL approaches and three GNNs. For these approaches we estimate these properties using point estimates such as MAP and mean. For SRL-based approaches that can infer a joint distribution over the missing attributes, we also estimate these properties as an expectation over the distribution. To compute the expectation tractably for probabilistic soft logic, one of the SRL approaches that we study, we introduce a novel sampling framework. In the experimental evaluation, using three benchmark datasets, we show that SRL-based approaches tend to outperform GNN-based approaches both in computing aggregate properties and predictive accuracy. Specifically, we show that estimating the aggregate properties as an expectation over the joint distribution outperforms point estimates.

A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However, the existing complementary-label learning methods cannot learn from the easily accessible unlabeled samples and samples with multiple complementary labels, which are more informative. In this paper, to remove these limitations, we propose the novel multi-complementary and unlabeled learning framework that allows unbiased estimation of classification risk from samples with any number of complementary labels and unlabeled samples, for arbitrary loss functions and models. We first give an unbiased estimator of the classification risk from samples with multiple complementary labels, and then further improve the estimator by incorporating unlabeled samples into the risk formulation. The estimation error bounds show that the proposed methods are in the optimal parametric convergence rate. Finally, the experiments on both linear and deep models show the effectiveness of our methods.

Solving many-objective problems (MaOPs) is still a significant challenge in the multi-objective optimization (MOO) field. One way to measure algorithm performance is through the use of benchmark functions (also called test functions or test suites), which are artificial problems with a well-defined mathematical formulation, known solutions and a variety of features and difficulties. In this paper we propose a parameterized generator of scalable and customizable benchmark problems for MaOPs. It is able to generate problems that reproduce features present in other benchmarks and also problems with some new features. We propose here the concept of generative benchmarking, in which one can generate an infinite number of MOO problems, by varying parameters that control specific features that the problem should have: scalability in the number of variables and objectives, bias, deceptiveness, multimodality, robust and non-robust solutions, shape of the Pareto front, and constraints. The proposed Generalized Position-Distance (GPD) tunable benchmark generator uses the position-distance paradigm, a basic approach to building test functions, used in other benchmarks such as Deb, Thiele, Laumanns and Zitzler (DTLZ), Walking Fish Group (WFG) and others. It includes scalable problems in any number of variables and objectives and it presents Pareto fronts with different characteristics. The resulting functions are easy to understand and visualize, easy to implement, fast to compute and their Pareto optimal solutions are known.

Motivation Interoperability has been a challenging unsolved problem that relies on manual, error-prone solutions and costs bill ions of dollars annually [2, 3]. Semi-automated verification of interoperability can be achieved by a set of limited tools. However, there does not exist any automated tools for the verification and the validation of interoperability soluti ons. This work may enable the next generation of automatically composable and reconfigurable systems, and support formal verification of the currently used standards. In this articl e, we focus on the theoretical framework we built in [1], and construct an algorithmic framework that can be used to apply the theory presented in [1]. W e also provide practical applicat ions using the automated system we built based on the algorithmic framework we present here. To our knowledge, there does not exist any work in the literature which has developed an algorithmic framework or an automated system that is capable of testing for the interope r-ability of CAD systems based on the interchangeability of th eir models with respect to their shape properties. By construct ing such a framework and a system, we aim to show that it is possible to discover the interoperability between CAD syst ems with a predetermined tolerance without translating forma ts or converting representations.