Survival analysis in the presence of multiple possible adverse events, i.e., competing risks, is a pervasive problem in many industries (healthcare, finance, etc.). Since only one event is typically observed, the incidence of an event of interest is often obscured by other related competing events. This nonidentifiability, or inability to estimate true cause-specific survival curves from empirical data, further complicates competing risk survival analysis. We introduce Siamese Survival Prognosis Network (SSPN), a novel deep learning architecture for estimating personalized risk scores in the presence of competing risks. SSPN circumvents the nonidentifiability problem by avoiding the estimation of cause-specific survival curves and instead determines pairwise concordant time-dependent risks, where longer event times are assigned lower risks. Furthermore, SSPN is able to directly optimize an approximation to the C-discrimination index, rather than relying on well-known metrics which are unable to capture the unique requirements of survival analysis with competing risks.

We show that the output of a (residual) convolutional neural network (CNN) with an appropriate prior over the weights and biases is a Gaussian process (GP) in the limit of infinitely many convolutional filters, extending similar results for dense networks. For a CNN, the equivalent kernel can be computed exactly and, unlike "deep kernels", has very few parameters: only the hyperparameters of the original CNN. Further, we show that this kernel has two properties that allow it to be computed efficiently; the cost of evaluating the kernel for a pair of images is similar to a single forward pass through the original CNN with only one filter per layer.

Accurate time-series forecasting is vital for numerous areas of application such as transportation, energy, finance, economics, etc. However, while modern techniques are able to explore large sets of temporal data to build forecasting models, they typically neglect valuable information that is often available under the form of unstructured text. Although this data is in a radically different format, it often contains contextual explanations for many of the patterns that are observed in the temporal data. In this paper, we propose two deep learning architectures that leverage word embeddings, convolutional layers and attention mechanisms for combining text information with time-series data. We apply these approaches for the problem of taxi demand forecasting in event areas. Using publicly available taxi data from New York, we empirically show that by fusing these two complementary cross-modal sources of information, the proposed models are able to significantly reduce the error in the forecasts. Keywords: Deep learning, Data fusion, Cross modality learning, Time series forecasting, Textual data, Taxi demand, Special events, Urban mobility 1. Introduction Understanding what drives the travel behavior of people is a key research topic for developing effective and efficient intelligent transportation systems that adapt to the travel demand. However, typical approaches focus only on capturing recurrent mobility trends that relate to habitual/routine behaviour [1], and on exploiting short-term correlations with recent observation patterns [2, 3]. While this type of approaches can be successful for long-term planning applications or for modeling demand in non-eventful areas such as residential neighborhoods, in lively and highly dynamic areas that are prone to the occurrence of multiple special events, such as music concerts, sports games, festivals, parades and protests, these approaches fail to accurately model mobility demand [4]. As we move towards the deployment of autonomous vehicles, understanding and being able to anticipate mobility demand becomes crucial, especially in shared-mobility scenarios, as this allows for properly managing fleets and increasing user-satisfaction. In order to capture the effects of events, one can exploit the vast amount of information that is shared online about what is planned to take place in the city. However, most of this information is typically in the form of unstructured natural-language text.

Deep learning has recently been shown to be instrumental in the problem of domain adaptation, where the goal is to learn a model on a target domain using a similar --but not identical-- source domain. The rationale for coupling both techniques is the possibility of extracting common concepts across domains. Considering (strictly) local representations, traditional deep learning assumes common concepts must be captured in the same hidden units. We contend that jointly training a model with source and target data using a single deep network is prone to failure when there is inherently lower-level representational discrepancy between the two domains; such discrepancy leads to a misalignment of corresponding concepts in separate hidden units. We introduce a search framework to correctly align high-level representations when training deep networks; such framework leads to the notion of conceptual --as opposed to representational-- domain adaptation.

The Dynamic Chain Event Graph (DCEG) is able to depict many classes of discrete random processes exhibiting asymmetries in their developments and context-specific conditional probabilities structures. However, paradoxically, this very generality has so far frustrated its wide application. So in this paper we develop an object-oriented method to fully analyse a particularly useful and feasibly implementable new subclass of these graphical models called the N Time-Slice DCEG (NT-DCEG). After demonstrating a close relationship between an NT-DCEG and a specific class of Markov processes, we discuss how graphical modellers can exploit this connection to gain a deep understanding of their processes. We also show how to read from the topology of this graph context-specific independence statements that can then be checked by domain experts. Our methods are illustrated throughout using examples of dynamic multivariate processes describing inmate radicalisation in a prison.

Sequence generative adversarial networks (SeqGAN) have been used to improve conditional sequence generation tasks, for example, chit-chat dialogue generation. To stabilize the training of SeqGAN, Monte Carlo tree search (MCTS) or reward at every generation step (REGS) is used to evaluate the goodness of a generated subsequence. MCTS is computationally intensive, but the performance of REGS is worse than MCTS. In this paper, we propose stepwise GAN (StepGAN), in which the discriminator is modified to automatically assign scores quantifying the goodness of each subsequence at every generation step. StepGAN has significantly less computational costs than MCTS. We demonstrate that StepGAN outperforms previous GAN-based methods on both synthetic experiment and chit-chat dialogue generation.

Stochastic gradient descent (SGD) (Robbins and Monro, 1951) and its variants have been widely used in training deep neural networks. Among those variants, adaptive gradient methods (AdaGrad) (Duchi et al., 2011; McMahan and Streeter, 2010), which scale each coordinate of the gradient by a function of past gradients, can achieve better performance than vanilla SGD in practice when the gradients are sparse. An intuitive explanation for the success of AdaGrad is that it automatically adjusts the learning rate for each feature based on the partial gradient, which accelerates the convergence. However, AdaGrad was later found to demonstrate degraded performance especially in cases where the loss function is nonconvex or the gradient is dense, due to rapid decay of learning rate.

Generalising well in supervised learning tasks relies on correctly extrapolating the training data to a large region of the input space. One way to achieve this is to constrain the predictions to be invariant to transformations on the input that are known to be irrelevant (e.g. translation). Commonly, this is done through data augmentation, where the training set is enlarged by applying hand-crafted transformations to the inputs. We argue that invariances should instead be incorporated in the model structure, and learned using the marginal likelihood, which correctly rewards the reduced complexity of invariant models. We demonstrate this for Gaussian process models, due to the ease with which their marginal likelihood can be estimated. Our main contribution is a variational inference scheme for Gaussian processes containing invariances described by a sampling procedure. We learn the sampling procedure by back-propagating through it to maximise the marginal likelihood.

Reinventing the future of work can lead to shared prosperity. An artificial intelligence-driven career adviser, an industrial smart glove, freelance insurance, a tactile laptop for the visually impaired. The 12 European finalists of the global MIT Inclusive Innovation Challenge are "improving economic opportunity for workers," according to the MIT Initiative on the Digital Economy. The challenge is the flagship program of the initiative, and this year the initiative launched a worldwide competition divided into five regions: North America, Latin America, Europe, Africa, and Asia. "If we employ inclusive innovation globally, it could be the best thing that ever happened to humanity," Erik Brynjolfsson, director of the initiative, said in a statement.

Exponential advancements in technology within the last half century have profoundly reshaped humanity and continue to do so continuously. Concepts which once seemed as fantasy Sci-Fi, visualized through Hollywood hits such as The Terminator (1984) and Eagle Eye (2008) have steadily and inconspicuously become a part of our reality. More recently, the futurist show, Black Mirror (2011) featured on Netflix gives us a glimpse of what the future may hold. One thing in common for all of these shows is the portrayal of possibilities with regards to advancements in computer technology -- be it in the form of a highly intelligent, autonomous, sophisticated robot like the Terminator (with a massive capacity for destruction)or ARIIA, a supercomputer able to manipulate almost all connected devices and command its victims to fulfill its agenda. Artificial Intelligence (AI) is seen to be the core driver of current trends within the tech sector and has vastly developed since the term was first coined in the 1950's. It is embedded in our phones, in the form of online chat bots and as phone operators to name a few contemporary use cases.