Within the burgeoning expansion of deep learning and computer vision across the different fields of science, when it comes to urban development, deep learning and computer vision applications are still limited towards the notions of smart cities and autonomous vehicles. Indeed, a wide gap of knowledge appears when it comes to cities and urban regions in less developed countries where the chaos of informality is the dominant scheme. How can deep learning and Artificial Intelligence (AI) untangle the complexities of informality to advance urban modelling and our understanding of cities? Various questions and debates can be raised concerning the future of cities of the North and the South in the paradigm of AI and computer vision. In this paper, we introduce a new method for multipurpose realistic-dynamic urban modelling relying on deep learning and computer vision, using deep Convolutional Neural Networks (CNN), to sense and detect informality and slums in urban scenes from aerial and street view images in addition to detection of pedestrian and transport modes. The model has been trained on images of urban scenes in cities across the globe. The model shows a good validation of understanding a wide spectrum of nuances among the planned and the unplanned regions, including informal and slum areas. We attempt to advance urban modelling for better understanding the dynamics of city developments. We also aim to exemplify the significant impacts of AI in cities beyond how smart cities are discussed and perceived in the mainstream. The algorithms of the URBAN-i model are fully-coded in Python programming with the pre-trained deep learning models to be used as a tool for mapping and city modelling in the various corner of the globe, including informal settlements and slum regions.

Abstract--Recent years have witnessed an explosive growth of mobile devices. Mobile devices are permeating every aspect of our daily lives. With the increasing usage of mobile devices and intelligent applications, there is a soaring demand for mobile applications with machine learning services. Inspired by the tremendous success achieved by deep learning in many machine learning tasks, it becomes a natural trend to push deep learning towards mobile applications. However, there exist many challenges to realize deep learning in mobile applications, including the contradiction between the miniature nature of mobile devices and the resource requirement of deep neural networks, the privacy and security concerns about individuals' data, and so on. To resolve these challenges, during the past few years, great leaps have been made in this area. In this paper, we provide an overview of the current challenges and representative achievements about pushing deep learning on mobile devices from three aspects: training with mobile data, efficient inference on mobile devices, and applications of mobile deep learning. The former two aspects cover the primary tasks of deep learning. Then, we go through our two recent applications that apply the data collected by mobile devices to inferring mood disturbance and user identification. Finally, we conclude this paper with the discussion of the future of this area. The past few years have witnessed an explosive growth of mobile devices which is expected to continue in the next decades. It is predicted that mobile devices will reach 5.6 billion, accounting for 21% of all networked devices in 2020 [1].

To apply general knowledge to machine reading comprehension (MRC), we propose an innovative MRC approach, which consists of a WordNet-based data enrichment method and an MRC model named as Knowledge Aided Reader (KAR). The data enrichment method uses the semantic relations of WordNet to extract semantic level inter-word connections from each passage-question pair in the MRC dataset, and allows us to control the amount of the extraction results by setting a hyper-parameter. KAR uses the extraction results of the data enrichment method as explicit knowledge to assist the prediction of answer spans. According to the experimental results, the single model of KAR achieves an Exact Match (EM) of $72.4$ and an F1 Score of $81.1$ on the development set of SQuAD, and more importantly, by applying different settings in the data enrichment method to change the amount of the extraction results, there is a $2\%$ variation in the resulting performance of KAR, which implies that the explicit knowledge provided by the data enrichment method plays an effective role in the training of KAR.

Research on link prediction in knowledge graphs has mainly focused on static multi-relational data. In this work we consider temporal knowledge graphs where relations between entities may only hold for a time interval or a specific point in time. In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations. To incorporate temporal information, we utilize recurrent neural networks to learn time-aware representations of relation types which can be used in conjunction with existing latent factorization methods. The proposed approach is shown to be robust to common challenges in real-world KGs: the sparsity and heterogeneity of temporal expressions. Experiments show the benefits of our approach on four temporal KGs. The data sets are available under a permissive BSD-3 license 1.

This paper presents a new deep learning architecture for Natural Language Inference (NLI). Firstly, we introduce a new architecture where alignment pairs are compared, compressed and then propagated to upper layers for enhanced representation learning. Secondly, we adopt factorization layers for efficient and expressive compression of alignment vectors into scalar features, which are then used to augment the base word representations. The design of our approach is aimed to be conceptually simple, compact and yet powerful. We conduct experiments on three popular benchmarks, SNLI, MultiNLI and SciTail, achieving competitive performance on all. A lightweight parameterization of our model also enjoys a $\approx 3$ times reduction in parameter size compared to the existing state-of-the-art models, e.g., ESIM and DIIN, while maintaining competitive performance. Additionally, visual analysis shows that our propagated features are highly interpretable.

While deep reinforcement learning (deep RL) agents are effective at maximizing rewards, it is often unclear what strategies they use to do so. In this paper, we take a step toward explaining deep RL agents through a case study using Atari 2600 environments. In particular, we focus on using saliency maps to understand how an agent learns and executes a policy. We introduce a method for generating useful saliency maps and use it to show 1) what strong agents attend to, 2) whether agents are making decisions for the right or wrong reasons, and 3) how agents evolve during learning. We also test our method on non-expert human subjects and find that it improves their ability to reason about these agents. Overall, our results show that saliency information can provide significant insight into an RL agent's decisions and learning behavior.

Click-through rate~(CTR) prediction, whose goal is to estimate the probability of the user clicks, has become one of the core tasks in advertising systems. For CTR prediction model, it is necessary to capture the latent user interest behind the user behavior data. Besides, considering the changing of the external environment and the internal cognition, user interest evolves over time dynamically. There are several CTR prediction methods for interest modeling, while most of them regard the representation of behavior as the interest directly, and lack specially modeling for latent interest behind the concrete behavior. Moreover, few work consider the changing trend of interest. In this paper, we propose a novel model, named Deep Interest Evolution Network~(DIEN), for CTR prediction. Specifically, we design interest extractor layer to capture temporal interests from history behavior sequence. At this layer, we introduce an auxiliary loss to supervise interest extracting at each step. As user interests are diverse, especially in the e-commerce system, we propose interest evolving layer to capture interest evolving process that is relative to the target item. At interest evolving layer, attention mechanism is embedded into the sequential structure novelly, and the effects of relative interests are strengthened during interest evolution. In the experiments on both public and industrial datasets, DIEN significantly outperforms the state-of-the-art solutions. Notably, DIEN has been deployed in the display advertisement system of Taobao, and obtained 20.7\% improvement on CTR.

The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined Deep Learning, revolutionized the area of artificial intelligence, machine learning, and data analysis. More recently, these methods have been applied to the numerical solution of high dimensional PDEs with great success. In particular, recent simulations indicate that deep learning based algorithms are capable of overcoming the curse of dimensionality for the numerical solution of linear Kolmogorov PDEs. Kolmogorov PDEs have been widely used in models from engineering, finance, and the natural sciences. Nearly all approximation methods for Kolmogorov PDEs in the literature suffer under the curse of dimensionality. By contrast, in recent work by some of the authors it was shown that deep ReLU neural networks are capable of approximating solutions of Kolmogorov PDEs without incurring the curse of dimensionality. The present paper considerably strengthens these results by providing an analysis of the generalization error. In particular we show that for Kolmogorov PDEs with affine drift and diffusion coefficients and a given accuracy $\varepsilon>0$, ERM over deep neural network hypothesis classes of size scaling polynomially in the dimension $d$ and $\varepsilon^{-1}$ and with a number of training samples scaling polynomially in the dimension $d$ and $\varepsilon^{-1}$ approximates the solution of the Kolmogorov PDE to within accuracy $\varepsilon$ with high probability. We conclude that ERM over deep neural network hypothesis classes breaks the curse of dimensionality for the numerical solution of linear Kolmogorov PDEs with affine drift and diffusion coefficients. To the best of our knowledge this is the first rigorous mathematical result that proves the efficiency of deep learning methods for high dimensional problems.

We study discrete time dynamical systems governed by the state equation $h_{t+1}=\phi(Ah_t+Bu_t)$. Here $A,B$ are weight matrices, $\phi$ is an activation function, and $u_t$ is the input data. This relation is the backbone of recurrent neural networks (e.g. LSTMs) which have broad applications in sequential learning tasks. We utilize stochastic gradient descent to learn the weight matrices from a finite input/state trajectory $(u_t,h_t)_{t=0}^N$. We prove that SGD estimate linearly converges to the ground truth weights while using near-optimal sample size. Our results apply to increasing activations whose derivatives are bounded away from zero. The analysis is based on i) a novel SGD convergence result with nonlinear activations and ii) careful statistical characterization of the state vector. Numerical experiments verify the fast convergence of SGD on ReLU and leaky ReLU in consistence with our theory.

We consider the problem of performing classification when only binary measurements of data are available. This situation may arise due to the need for extreme compression of data or in the interest of hardware efficiency [11, 17, 18, 1]. Despite this extremely coarse quantization of the data, one can still perform learning tasks, such as classification, with high accuracy. The authors of [23] recently proposed a classification method for binary data, which they show to be reasonably accurate and sufficiently simple to allow for theoretical analysis in certain settings. Additionally, the predicted class can be approximately understood as the class whose binarized training data most closely and frequently matches that of the test point. As this approach will be the foundation of the work presented here, we discuss it in detail in the next section. Interpretability of algorithms and the ability to explain predictions is of increasing importance as machine learning algorithms are applied to an expanding range of problems in areas such as medicine, criminal justice, and finance [3, 2, 24]. Decisions made based on algorithmic predictions can have profound repercussions for both participating individuals as well as society at large. A major drawback to complex models such as deep neural networks [20, 15, 8, 19] is that it is extremely difficult to explain how or why such algorithms arrive at a specific prediction, see e.g.