As more and more people shift their movie watching online, competition between movie viewing websites are getting more and more intense. Therefore, it has become incredibly important to accurately predict a given user's watching list to maximize the chances of keeping the user on the platform. Recent studies have suggested that the novelty-seeking propensity of users can impact their viewing behavior. In this paper, we aim to accurately model and describe this novelty-seeking trait across many users and timestamps driven by data, taking into consideration user forgetfulness. Compared to previous studies, we propose a more robust measure for novelty. Our model, termed Deep Forgetful Novelty-Seeking Model (DFNSM), leverages demographic information about users, genre information about movies, and novelty-seeking traits to predict the most likely next actions of a user. To evaluate the performance of our model, we conducted extensive experiments on a large movie rating dataset. The results reveal that DFNSM is very effective for movie recommendation.

This work builds an automated anomaly detection method for chaotic time series, and more concretely for turbulent, high-dimensional, ocean simulations. We solve this task by extending the Echo State Network by spatially aware input maps, such as convolutions, gradients, cosine transforms, et cetera, as well as a spatially aware loss function. The spatial ESN is used to create predictions which reduce the detection problem to thresholding of the prediction error. We benchmark our detection framework on different tasks of increasing difficulty to show the generality of the framework before applying it to raw climate model output in the region of the Japanese ocean current Kuroshio, which exhibits a bimodality that is not easily detected by the naked eye. The code is available as an open source Python package, Torsk, available at https://github.com/nmheim/torsk, where we also provide supplementary material and programs that reproduce the results shown in this paper.

In this paper, the artificial neural network (ANN) is functio nalized utilizing the activation integral, so its principle and design can be easily deduced. In the first part, the linear activation function is abstracted from normal activ ation functions, and the activation integral in continuous form is established. Then the discre te form of activation integral of composite function and multivariate function are introduc ed. Finally, the standard discrete activation integral of any function is derived, which is the discrete activation integral with linear activation function integrated. In the second part, the activation integral theory is introduced into ANN, and the main network structure types ar e analyzed, and the corresponding function forms are obtained.

Partial Differential Equations (PDE) are fundamental to model different phenomena in science and engineering mathematically. Solving them is a crucial step towards a precise knowledge of the behaviour of natural and engineered systems. In general, in order to solve PDEs that represent real systems to an acceptable degree, analytical methods are usually not enough. One has to resort to discretization methods. For engineering problems, probably the best known option is the finite element method (FEM). However, powerful alternatives such as mesh-free methods and Isogeometric Analysis (IGA) are also available. The fundamental idea is to approximate the solution of the PDE by means of functions specifically built to have some desirable properties. In this contribution, we explore Deep Neural Networks (DNNs) as an option for approximation. They have shown impressive results in areas such as visual recognition. DNNs are regarded here as function approximation machines. There is great flexibility to define their structure and important advances in the architecture and the efficiency of the algorithms to implement them make DNNs a very interesting alternative to approximate the solution of a PDE. We concentrate in applications that have an interest for Computational Mechanics. Most contributions that have decided to explore this possibility have adopted a collocation strategy. In this contribution, we concentrate in mechanical problems and analyze the energetic format of the PDE. The energy of a mechanical system seems to be the natural loss function for a machine learning method to approach a mechanical problem. As proofs of concept, we deal with several problems and explore the capabilities of the method for applications in engineering.

The task can be modeled as building a graph for a given text, whose nodes represent events and edges are labeled with temporal relations correspondingly. Figure 1a illustrates such a graph for the text shown therein. The nodes assassination, slaughtered, rampage, war, and Hutu are the candidate events, and different types of edges specify different temporal relations between them: assassination is BEFORE rampage, rampage INCLUDES slaughtered, and the relation between slaughtered and war is VAGUE. Since "Hutu" is actually not an event, a system is expected to annotate the relations between "Hutu" and all other nodes in the graph as NONE (i.e., no relation). As far as we know, all existing systems treat this task as a pipeline of two separate subtasks, (a) Temporal Relation Graph (b) Pipeline Model (c) Structured Joint Model Figure 1: An illustration of event and relation models in our proposed joint framework.

More and more users and developers are using Issue Tracking Systems (ITSs) to report issues, including bugs, feature requests, enhancement suggestions, etc. Different information, however, is gathered from users when issues are reported on different ITSs, which presents considerable challenges for issue classification tools to work effectively across the ITSs. Besides, bugs often take higher priority when it comes to classifying the issues, while existing approaches to issue classification seldom focus on distinguishing bugs and the other non-bug issues, leading to suboptimal accuracy in bug identification. In this paper, we propose a deep learning-based approach to automatically identify bug-reporting issues across various ITSs. The approach implements the k-NN algorithm to detect and correct misclassifications in data extracted from the ITSs, and trains an attention-based bi-directional long short-term memory (ABLSTM) network using a dataset of over 1.2 million labelled issues to identify bug reports. Experimental evaluation shows that our approach achieved an F-measure of 85.6\% in distinguishing bugs and other issues, significantly outperforming the other benchmark and state-of-the-art approaches examined in the experiment.

This paper presents a new approach of automatic text summarization which combines domain oriented text analysis (DoTA) and rhetorical structure theory (RST) in a grammar form: the attributed rhetorical structure grammar (ARSG), where the non-terminal symbols are domain keywords, called domain relations, while the rhetorical relations serve as attributes. We developed machine learning algorithms for learning such a grammar from a corpus of sample domain texts, as well as parsing algorithms for the learned grammar, together with adjustable text summarization algorithms for generating domain specific summaries. Our practical experiments have shown that with support of domain knowledge the drawback of missing very large training data set can be effectively compensated. We have also shown that the knowledge based approach may be made more powerful by introducing grammar parsing and RST as inference engine. For checking the feasibility of model transfer, we introduced a technique for mapping a grammar from one domain to others with acceptable cost. We have also made a comprehensive comparison of our approach with some others.

Imitation learning is becoming more and more successful for autonomous driving. End-to-end (raw signal to command) performs well on relatively simple tasks (lane keeping and navigation). Mid-to-mid (environment abstraction to mid-level trajectory representation) or direct perception (raw signal to performance) approaches strive to handle more complex, real life environment and tasks (e.g. In this work, we show that complex urban situations can be handled with raw signal input and mid-level representation. W e build a hybrid end-to-mid approach predicting trajectories for neighbor vehicles and for the ego vehicle with a conditional navigation goal. W e propose an original architecture inspired from social pooling LSTM taking low and mid level data as input and producing trajectories as polynomials of time. W e introduce a label augmentation mechanism to get the level of generalization that is required to control a vehicle. The performance is evaluated on CARLA 0.8 benchmark, showing significant improvements over previously published state of the art. 1. Introduction Modular pipelines [32] are the most used approach to autonomous driving. The advantage is that the modules are interpretable and relatively mature, in particular on the perception side with the success of deep learning for object detection ([13, 20] among many others). However, the complexity of the interactions in the real world causes the pipeline to be also complex, especially in the planning and decision modules.

The repaired code example in Figure 3b deletes assignment operator " ", and inserts an equality operator " ". Hence its set of repair tokens are {, - }. D. Error Repair Class Given a buggy source program that suffers from compilation errors ( E s) which require a set of repair tokens ( R s) to fix, its error-repair class ( C) is defined as the merged set of errors and repairs {E s R s}. For example, the erroneous-repaired code pair in Figure 3 belongs to C 8 {E 10 - }, the 8 th most frequently occurring error-repair class. We determine the error-repair class of the 23, 275 erroneous-repaired code pairs in our dataset. Table III lists the error-repair classes ( C s) sorted in decreasing order of frequency, along with the number of buggy programs belonging to each class.

For each dialogue turn, a DST module takes a user utterance and the dialogue history as input, and outputs a belief estimate of the dialogue state. Then a machine action is decided based on the dialogue state according to a dialogue policy module, after which a machine response is generated. Traditionally, a dialogue state consists of a set of requests and joint goals, both of which are represented by a set of slot-value pairs (e.g. ( request, phone), ( area, north), ( food, Japanese)) (Henderson et al., 2014). In a recently proposed multi-DST Models ITC NBT -CNN (Mrksic et al., 2017) O (mn) MD-DST (Rastogi et al., 2017) O (n) GLAD (Zhong et al., 2018) O (mn) StateNet PSI (Ren et al., 2018) O (n) TRADE (Wu et al., 2019) O (n) HyST (Goel et al., 2019) O (n) DSTRead (Gao et al., 2019) O (n) Table 1: The Inference Time Complexity (ITC) of previous DST models. The ITC is calculated based on how many times inference must be performed to complete a prediction of the belief state in a dialogue turn, where m is the number of values in a predefined ontology list and n is the number of slots.