The state of the art practice in robotics planning is to script behaviors manually, where each behavior is typically generated using trajectory optimization. However, in order for robots to be able to act robustly and adapt to novel situations, they need to plan these activity sequences autonomously. Since the conditions and effects of these behaviors are tightly coupled through time, state and control variables, many problems require that the tasks of activity planning and trajectory optimization are considered together. There are two key issues underlying effective hybrid activity and trajectory planning: the sufficiently accurate modeling of robot dynamics and the capability of planning over long horizons. Hybrid activity and trajectory planners that employ mixed integer programming within a discrete time formulation are able to accurately model complex dynamics for robot vehicles, but are often restricted to relatively short horizons. On the other hand, current hybrid activity planners that employ continuous time formulations can handle longer horizons but they only allow actions to have continuous effects with constant rate of change, and restrict the allowed state constraints to linear inequalities. This is insufficient for many robotic applications and it greatly limits the expressivity of the problems that these approaches can solve. In this work we present the ScottyActivity planner, that is able to generate practical hybrid activity and motion plans over long horizons by employing recent methods in convex optimization combined with methods for planning with relaxed plan graphs and heuristic forward search. Unlike other continuous time planners, ScottyActivity can solve a broad class of robotic planning problems by supporting convex quadratic constraints on state variables and control variables that are jointly constrained and that affect multiple state variables simultaneously. In order to support planning over long horizons, ScottyActivity does not resort to time, state or control variable discretization. While straightforward formulations of consistency checks are not convex and do not scale, we present an efficient convex formulation, in the form of a Second Order Cone Program (SOCP), that is very fast to solve. We also introduce several new realistic domains that demonstrate the capabilities and scalability of our approach, and their simplified linear versions, that we use to compare with other state of the art planners. This work demonstrates the power of integrating advanced convex optimization techniques with discrete search methods and paves the way for extensions dealing with non-convex disjoint constraints, such as obstacle avoidance.

To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentences are available as training data because collecting enough OOD sentences in an unbiased way is a laborious and time-consuming job. This paper proposes a novel neural sentence embedding method that represents sentences in a low-dimensional continuous vector space that emphasizes aspects that distinguish ID cases from OOD cases. We first used a large set of unlabeled text to pre-train word representations that are used to initialize neural sentence embedding. Then we used domain-category analysis as an auxiliary task to train neural sentence embedding for OOD sentence detection. After the sentence representations were learned, we used them to train an autoencoder aimed at OOD sentence detection. We evaluated our method by experimentally comparing it to the state-of-the-art methods in an eight-domain dialog system; our proposed method achieved the highest accuracy in all tests.

Recently, link prediction has attracted more attentions from various disciplines such as computer science, bioinformatics and economics. In this problem, unknown links between nodes are discovered based on numerous information such as network topology, profile information and user generated contents. Most of the previous researchers have focused on the structural features of the networks. While the recent researches indicate that contextual information can change the network topology. Although, there are number of valuable researches which combine structural and content information, but they face with the scalability issue due to feature engineering. Because, majority of the extracted features are obtained by a supervised or semi supervised algorithm. Moreover, the existing features are not general enough to indicate good performance on different networks with heterogeneous structures. Besides, most of the previous researches are presented for undirected and unweighted networks. In this paper, a novel link prediction framework called "DeepLink" is presented based on deep learning techniques. In contrast to the previous researches which fail to automatically extract best features for the link prediction, deep learning reduces the manual feature engineering. In this framework, both the structural and content information of the nodes are employed. The framework can use different structural feature vectors, which are prepared by various link prediction methods. It considers all proximity orders that are presented in a network during the structural feature learning. We have evaluated the performance of DeepLink on two real social network datasets including Telegram and irBlogs. On both datasets, the proposed framework outperforms several structural and hybrid approaches for link prediction problem.

Recently, it was proposed to employ approximate quantum adders to implement quantum autoencoders in quantum technologies. Here, we carry out the experimental implementation of this proposal in the Rigetti cloud quantum computer employing up to three qubits. The experimental fidelities are in good agreement with the theoretical prediction, thus proving the feasibility to realize quantum autoencoders via quantum adders in state-of-the-art superconducting quantum technologies. A quantum autoencoder is a quantum device which can reshuffle and compress the quantum information of a subset of a Hilbert space spanned by initial n -qubit states onto n ′ qubit states with n ′ n [1, 2]. This approach may allow one to employ fewer quantum computing resources [3, 4]. On the other hand, recently it was proven that a general quantum adder performing the equal weight superposition of two unknown quantum states is forbidden in general [5].

Present but not The type of sound described is present, but the audio clip also predominant (PNP) contains other salient types of sound and/or strong background noise. Not Present (NP) The type of sound described is not present in the audio clip. Unsure (U) I am not sure whether the type of sound described is present or not. Table 2: Categories composing FSDKaggle2018, along with the number of samples and time (in minutes, rounded) in the train set. Percategory AP@3 achieved by the baseline system is reported using all the test files for every category (i.e., not following the public/private splits of the Kaggle leaderboard).

The conflict between increasing demand for computing and sluggish grow of hardware capability triggers the heated development of approximate computing, which has achieved massive success in both industry and research community. Many applications that do not require utterly accurate computation can achieve tremendous acceleration and drastic reduction of the energy consumption by leveraging approximate computing, especially in domains that call for real-time calculation, fast response and low power consumption such as learning [27], image processing [19] and scientific computation [24]. Approximation computing can be conduct in different hierarchies, such as hardware [6], [18], system and software levels. Various approximate computing architectures [17], [19], [27] are advocated. Neural network (NN) based approximate computing focus on the acceleration in software-level and has many advantages when compared to previous methods. First, neural networks are proved to be able to fit any continuous function [12], and thus this method can universally be adopted by different tasks. Second, enormous parallelism in the neural networks is exploited by the rapid advancement of various neural network accelerators.

In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e.g. same classes), but also different latent data structures (e.g. different acquisition conditions). In such a situation, the model will perform poorly on the new data, since the classifier is specialized to recognize visual cues specific to the source domain. In this work we explore a solution, named DeepJDOT, to tackle this problem: through a measure of discrepancy on joint deep representations/labels based on optimal transport, we not only learn new data representations aligned between the source and target domain, but also simultaneously preserve the discriminative information used by the classifier. We applied DeepJDOT to a series of visual recognition tasks, where it compares favorably against state-of-the-art deep domain adaptation methods.

Deep neural networks (DNNs) have achieved significant success in a variety of real world applications. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model size and the intensive computation. To address this issue, various compression and acceleration techniques have been investigated, among which low-rank filters and sparse filters are heavily studied. In this paper we propose a unified framework to compress the convolutional neural networks by combining these two strategies, while taking the nonlinear activation into consideration. The filer of a layer is approximated by the sum of a sparse component and a low-rank component, both of which are in favor of model compression. Especially, we constrain the sparse component to be structured sparse which facilitates acceleration. The performance of the network is retained by minimizing the reconstruction error of the feature maps after activation of each layer, using the alternating direction method of multipliers (ADMM). The experimental results show that our proposed approach can compress VGG-16 and AlexNet by over 4X. In addition, 2.2X and 1.1X speedup are achieved on VGG-16 and AlexNet, respectively, at a cost of less increase on error rate.

Do you want to find out which are the best frameworks or libraries for natural language processing (NLP) in Python? Do you want to mine the social web and summarise blog posts? There are a lot of NLP libraries on the internet, but finding the right fit for your project is difficult. Natural Language Toolkit is one of the most popular platforms for building Python programs. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenisation, stemming, tagging, parsing, and semantic reasoning.

The use of facial recognition software is growing in China--s universities, ostensibly to improve security, but concerns are growing that it is used for monitoring students -- including foreing students -- and teachers, creating massive data bases on student attendance and movements around campus. Peking University in Beijing now screens students entering the university--s south-western gate by using a camera to scan their faces in a trial that began at the end of June to see if the technology can replace the use of university identity cards. The system scans through a database of thousands of photographs taken for student and staff identity cards, using a powerful system to match the photograph against a database of thousands of others. Facial recognition devices have already been installed outside the university--s libraries, classrooms, student accommodation, sports facilities and computer centres, but these match a face to an existing photograph of that person on the database rather than sifting through the entire database. Photographs can be retaken in the guard room at the gates if the photos do not quite match, according to the university--s social media account on Sina Weibo, though it does not say what the failure rate is -- in particular for foreign students.