Structure is the most basic and important property of crystalline solids; it determines directly or indirectly most materials characteristics. However, predicting crystal structure of solids remains a formidable and not fully solved problem. Standard theoretical tools for this task are computationally expensive and at times inaccurate. Here we present an alternative approach utilizing machine learning for crystal structure prediction. We developed a tool called Crystal Structure Prediction Network (CRYSPNet) that can predict the Bravais lattice, space group, and lattice parameters of an inorganic material based only on its chemical composition. CRYSPNet consists of a series of neural network models, using as inputs predictors aggregating the properties of the elements constituting the compound. It was trained and validated on more than 100,000 entries from the Inorganic Crystal Structure Database. The tool demonstrates robust predictive capability and outperforms alternative strategies by a large margin. Made available to the public (at https://github.com/AuroraLHT/cryspnet), it can be used both as an independent prediction engine or as a method to generate candidate structures for further computational and/or experimental validation.

A small subset of explainability techniques developed initially for image recognition models has recently been applied for interpretability of 3D Convolutional Neural Network models in activity recognition tasks. Much like the models themselves, the techniques require little or no modification to be compatible with 3D inputs. However, these explanation techniques regard spatial and temporal information jointly. Therefore, using such explanation techniques, a user cannot explicitly distinguish the role of motion in a 3D model's decision. In fact, it has been shown that these models do not appropriately factor motion information into their decision. We propose a selective relevance method for adapting the 2D explanation techniques to provide motion-specific explanations, better aligning them with the human understanding of motion as conceptually separate from static spatial features. We demonstrate the utility of our method in conjunction with several widely-used 2D explanation methods, and show that it improves explanation selectivity for motion. Our results show that the selective relevance method can not only provide insight on the role played by motion in the model's decision -- in effect, revealing and quantifying the model's spatial bias -- but the method also simplifies the resulting explanations for human consumption.

An actively evolving model class for generative temporal models developed in the deep learning community are deep state space models (SSMs) which have a close connection to classic SSMs. In this work six new deep SSMs are implemented and evaluated for the identification of established nonlinear dynamic system benchmarks. The models and their parameter learning algorithms are elaborated rigorously. The usage of deep SSMs as a black-box identification model can describe a wide range of dynamics due to the flexibility of deep neural networks. Additionally, the uncertainty of the system is modelled and therefore one obtains a much richer representation and a whole class of systems to describe the underlying dynamics.

Despite the growing popularity of metric learning approaches, very little work has attempted to perform a fair comparison of these techniques for speaker verification. We try to fill this gap and compare several metric learning loss functions in a systematic manner on the VoxCeleb dataset. The first family of loss functions is derived from the cross entropy loss (usually used for supervised classification) and includes the congenerous cosine loss, the additive angular margin loss, and the center loss. The second family of loss functions focuses on the similarity between training samples and includes the contrastive loss and the triplet loss. We show that the additive angular margin loss function outperforms all other loss functions in the study, while learning more robust representations. Based on a combination of SincNet trainable features and the x-vector architecture, the network used in this paper brings us a step closer to a really-end-to-end speaker verification system, when combined with the additive angular margin loss, while still being competitive with the x-vector baseline. In the spirit of reproducible research, we also release open source Python code for reproducing our results, and share pretrained PyTorch models on torch.hub that can be used either directly or after fine-tuning.

Modeling eye movement indicative of expertise behavior is decisive in user evaluation. However, it is indisputable that task semantics affect gaze behavior. We present a novel approach to gaze scanpath comparison that incorporates convolutional neural networks (CNN) to process scene information at the fixation level. Image patches linked to respective fixations are used as input for a CNN and the resulting feature vectors provide the temporal and spatial gaze information necessary for scanpath similarity comparison.We evaluated our proposed approach on gaze data from expert and novice dentists interpreting dental radiographs using a local alignment similarity score. Our approach was capable of distinguishing experts from novices with 93% accuracy while incorporating the image semantics. Moreover, our scanpath comparison using image patch features has the potential to incorporate task semantics from a variety of tasks

Recently, deep neural networks (DNNs) have made great progress on automated diagnosis with chest X-rays images. However, DNNs are vulnerable to adversarial examples, which may cause misdiagnoses to patients when applying the DNN based methods in disease detection. Recently, there is few comprehensive studies exploring the influence of attack and defense methods on disease detection, especially for the multi-label classification problem. In this paper, we aim to review various adversarial attack and defense methods on chest X-rays. First, the motivations and the mathematical representations of attack and defense methods are introduced in details. Second, we evaluate the influence of several state-of-the-art attack and defense methods for common thorax disease classification in chest X-rays. We found that the attack and defense methods have poor performance with excessive iterations and large perturbations. To address this, we propose a new defense method that is robust to different degrees of perturbations. This study could provide new insights into methodological development for the community.

The Hawkes process has become a standard method for modeling self-exciting event sequences with different event types. A recent work generalizing the Hawkes process to a neurally self-modulating multivariate point process enables the capturing of more complex and realistic influences of past events on the future. However, this approach is limited by the number of event types, making it impossible to model the dynamics of evolving graph sequences, where each possible link between two nodes can be considered as an event type. The problem becomes even more dramatic when links are directional and labeled, since, in this case, the number of event types scales with the number of nodes and link types. To address this issue, we propose the Graph Hawkes Network to capture the dynamics of evolving graph sequences. Extensive experiments on large-scale temporal relational databases, such as temporal knowledge graphs, demonstrate the effectiveness of our approach.

Feature selection is an important topic in traditional machine learning [Li et al., 2018], which motivated a large number of widely adopted works, e.g., Lasso [Tibshirani, 1996]. In various cases, the process of obtaining input measurements requires considerable effort (e.g., time, money, technology). For example, in medical datasets input features may correspond to lab tests, medical imaging results, or even answers to questionnaires, which are expensive and slow to produce. Allowing oneself to to be able to accurately predict a response variable from a small set of input features is thus a desirable goal, which can be manifested in saving time, money, and sometimes even human lives. As a running example, consider the case of a patient complaining to a family doctor about not feeling well. The doctor then asks the patients several questions about his current condition and medical background, and may also ask the patient to do some lab tests. Implicitly, the doctor is aiming at quickly collecting relevant details on the patient that will allow her to have a clear understanding of the patients' medical status, and consequently decide on an appropriate action (e.g., medication prescription, admit for hospitalization etc.).

New machine translations (MT) technologies are emerging rapidly and with them, bold claims of achieving human parity such as: (i) the results produced approach "accuracy achieved by average bilingual human translators" (Wu et al., 2017b) or (ii) the "translation quality is at human parity when compared to professional human translators" (Hassan et al., 2018) have seen the light of day (Laubli et al., 2018). Aside from the fact that many of these papers craft their own definition of human parity, these sensational claims are often not supported by a complete analysis of all aspects involved in translation. Establishing the discrepancies between the strengths of statistical approaches to MT and the way humans translate has been the starting point of our research. By looking at MT output and linguistic theory, we were able to identify some remaining issues. The problems range from simple number and gender agreement errors to more complex phenomena such as the correct translation of aspectual values and tenses. Our experiments confirm, along with other studies (Bentivogli et al., 2016), that neural MT has surpassed statistical MT in many aspects. However, some problems remain and others have emerged. We cover a series of problems related to the integration of specific linguistic features into statistical and neural MT, aiming to analyse and provide a solution to some of them. Our work focuses on addressing three main research questions that revolve around the complex relationship between linguistics and MT in general. We identify linguistic information that is lacking in order for automatic translation systems to produce more accurate translations and integrate additional features into the existing pipelines. We identify overgeneralization or 'algorithmic bias' as a potential drawback of neural MT and link it to many of the remaining linguistic issues.

The question of whether artificial beings or machines could become self-aware or consciousness has been a philosophical question for centuries. The main problem is that self-awareness cannot be observed from an outside perspective and the distinction of whether something is really self-aware or merely a clever program that pretends to do so cannot be answered without access to accurate knowledge about the mechanism's inner workings. We review the current state-of-the-art regarding these developments and investigate common machine learning approaches with respect to their potential ability to become self-aware. We realise that many important algorithmic steps towards machines with a core consciousness have already been devised. For human-level intelligence, however, many additional techniques have to be discovered.