Maybe every paper abstract should have a mandatory field of what the limitations of the proposed approach are. That way some of the science miscommunications and hypes could maybe be avoided. The media is often tempted to report each tiny new advance in a field, be it AI or nanotechnology, as a great triumph that will soon fundamentally alter our world. Occasionally, of course, new discoveries are underreported. The transistor did not make huge waves when it was first introduced, and few people initially appreciated the full potential of the Internet.

Although Deep Learning is generally classified as a subdivision of Machine Learning, a clear distinction should be made between the two. Machine Learning refers to algorithms/methods that were developed in the pre-Deep Learning era. The pre-Deep Learning era is generally referred to as the period before 2011/2012. These algorithms and methods were the maxima that computing power at the time allowed. The advent of the GPU and the development of AlexNet combined with Big Data made classical Machine Learning algorithms ineffective and allowed Deep Learning to take hold.

--This study refers to a reverse question answering (reverse QA) procedure, in which machines proactively raise questions and humans supply answers. This procedure exists in many real human-machine interaction applications. A crucial problem in human-machine interaction is answer understanding. Existing solutions rely on mandatory option term selection to avoid automatic answer understanding. However, these solutions lead to unnatural human-computer interaction and harm user experience. T o this end, this study proposed a novel deep answer understanding network, called AntNet, for reverse QA. The network consists of three new modules, namely, skeleton extraction for questions, relevance-aware representation of answers, and multi-hop based fusion. As answer understanding for reverse QA has not been explored, a new data corpus is compiled in this study. Experimental results indicate that our proposed network is significantly better than existing methods and those modified from classical natural language processing (NLP) deep models. The effectiveness of the three new modules is also verified. UTOMA TIC question answering (QA) is a crucial component in many human-machine interaction systems, such as intelligent customer service, as it can provide a natural way for humans to acquire information [1]. Therefore, QA has received increasing attention in academic research and industry communities in recent years [2]. Questions are solely raised by humans, and answers are then returned by machines in the conventional QA scenario. How to select the best matched answer is the key problem in this setting [3].

To determine whether deep learning-based algorithms applied to breast MR images can aid in the prediction of occult invasive disease following the diagnosis of ductal carcinoma in situ (DCIS) by core needle biopsy. The data was collected from 2000 to 2014. In this institutional review board-approved study, we analyzed dynamic contrast-enhanced fat-saturated T1-weighted MRI sequences from 131 patients with a core needle biopsy-confirmed diagnosis of DCIS. We explored two different deep learning approaches to predict whether there was an occult invasive component in the analyzed tumors that was ultimately identified at surgical excision. In the first approach, we adopted the transfer learning strategy.

Nowadays, collaborative filtering recommender systems have been widely deployed in many commercial companies to make profit. Neighbourhood-based collaborative filtering is common and effective. To date, despite its effectiveness, there has been little effort to explore their robustness and the impact of data poisoning attacks on their performance. Can the neighbourhood-based recommender systems be easily fooled? To this end, we shed light on the robustness of neighbourhood-based recommender systems and propose a novel data poisoning attack framework encoding the purpose of attack and constraint against them. We firstly illustrate how to calculate the optimal data poisoning attack, namely UNAttack. We inject a few well-designed fake users into the recommender systems such that target items will be recommended to as many normal users as possible. Extensive experiments are conducted on three real-world datasets to validate the effectiveness and the transferability of our proposed method. Besides, some interesting phenomenons can be found. For example, 1) neighbourhood-based recommender systems with Euclidean Distance-based similarity have strong robustness. 2) the fake users can be transferred to attack the state-of-the-art collaborative filtering recommender systems such as Neural Collaborative Filtering and Bayesian Personalized Ranking Matrix Factorization.

The rapid growth of deep learning applications in real life is accompanied by severe safety concerns. To mitigate this uneasy phenomenon, much research has been done providing reliable evaluations of the fragility level in different deep neural networks. Apart from devising adversarial attacks, quantifiers that certify safeguarded regions have also been designed in the past five years. The summarizing work of Salman et al. unifies a family of existing verifiers under a convex relaxation framework. We draw inspiration from such work and further demonstrate the optimality of deterministic CROWN (Zhang et al. 2018) solutions in a given linear programming problem under mild constraints. Given this theoretical result, the computationally expensive linear programming based method is shown to be unnecessary. We then propose an optimization-based approach \textit{FROWN} (\textbf{F}astened C\textbf{ROWN}): a general algorithm to tighten robustness certificates for neural networks. Extensive experiments on various networks trained individually verify the effectiveness of FROWN in safeguarding larger robust regions.

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce mis-classification in a large fraction of images of a specific class. Unlike previous methods that use iterative optimization for computing a universal perturbation, the proposed method employs a perturbation that is a linear function of weights of the neural network and hence can be computed much faster. The method does not require any training data and has no hyper-parameters. We also study the characteristics of the decision boundaries learned by standard and adversarially trained models to understand the universal adversarial perturbations. The vulnerability of state-of-the-art neural networks to adversarial perturbations was first studied in (Szegedy et al., 2014).

Moving Object Detection (MOD) is a critical task for autonomous vehicles as moving objects represent higher collision risk than static ones. The trajectory of the ego-vehicle is planned based on the future states of detected moving objects. It is quite challenging as the ego-motion has to be modelled and compensated to be able to understand the motion of the surrounding objects. In this work, we propose a real-time end-to-end CNN architecture for MOD utilizing spatio-temporal context to improve robustness. We construct a novel time-aware architecture exploiting temporal motion information embedded within sequential images in addition to explicit motion maps using optical flow images.We demonstrate the impact of our algorithm on KITTI dataset where we obtain an improvement of 8% relative to the baselines. We compare our algorithm with state-of-the-art methods and achieve competitive results on KITTI-Motion dataset in terms of accuracy at three times better run-time. The proposed algorithm runs at 23 fps on a standard desktop GPU targeting deployment on embedded platforms.

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that "similar objects should belong to the same group", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We show state-of-the-art results on clustering and image retrieval on several datasets, and show the potential of our method when combined with other techniques such as ensembles

Machine learning models can be used for pattern recognition in medical data in order to improve patient outcomes, such as the prediction of in-hospital mortality. Deep learning models, in particular, require large amounts of data for model training. However, the data is often collected at different hospitals and sharing is restricted due to patient privacy concerns. In this paper, we aimed to demonstrate the potential of distributed training in achieving state-of-the-art performance while maintaining data privacy. Our results show that training the model in the federated learning framework leads to comparable performance to the traditional centralised setting. We also suggest several considerations for the success of such frameworks in future work.