The safety of quadrotor has received increasing attention, and fault-tolerant control for complete actuator failures presents significant challenges. An adaptive robust fault-tolerant control framework is proposed in this paper, capable of uniformly handling situations from fault-free case to complete actuator failures, without controller switching. Actuator faults are actively compensated by two adaptive methods: firstly, direct adaptation is designed for the control input efficiency coefficients; and secondly, the filtering-based disturbance estimation is integrated to address lumped disturbances. To avoid hard switching of controllers and achieve unified fault-tolerant control, the attitude control employs the primary-axis control method. This is combined with an optimization-based prioritized control allocation, which prioritizes the control of force direction while sacrificing yaw angle tracking in the event of severe actuator failures. Numerical simulation demonstrates that the proposed controller can actively tolerate unpredictable complete actuator failures. Moreover, the integration of two fault compensation methods enhances fault tolerance performance than one method alone.

Neural machine translation (NMT) heavily relies on its encoder to capture the underlying meaning of a source sentence so as to generate a faithful translation. However, most NMT encoders are built upon either unidirectional or bidirectional recurrent neural networks, which either do not deal with future context or simply concatenate the history and future context to form context-dependent word representations, implicitly assuming the independence of the two types of contextual information. In this paper, we propose a novel context-aware recurrent encoder (CAEncoder), as an alternative to the widely-used bidirectional encoder, such that the future and history contexts can be fully incorporated into the learned source representations. Our CAEncoder involves a two-level hierarchy: The bottom level summarizes the history information, whereas the upper level assembles the summarized history and future context into source representations. Additionally, CAEncoder is as efficient as the bidirectional RNN encoder in terms of both training and decoding. Experiments on both Chinese-English and English-German translation tasks show that CAEncoder achieves significant improvements over the bidirectional RNN encoder on a widely-used NMT system.

Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing. In this paper, we explore a bilingual autoencoder approach to model parallel sentences. We extract sentence-level global descriptors (e.g. min, max) from word embeddings, and construct two monolingual autoencoders over these descriptors on the source and target language. In order to tightly connect the two autoencoders with bilingual correspondences, we force them to share the same decoding parameters and minimize a corpus-level semantic distance between the two languages. Being optimized towards a joint objective function of reconstruction and semantic errors, our bilingual antoencoder is able to learn continuous-valued latent representations for parallel sentences. Experiments on both intrinsic and extrinsic evaluations on statistical machine translation tasks show that our autoencoder achieves substantial improvements over the baselines.

Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence.In this paper, we propose a variational model to learn this conditional distribution for neural machine translation: a variational encoderdecoder model that can be trained end-to-end.Different from the vanilla encoder-decoder model that generates target translations from hidden representations of source sentences alone, the variational model introduces a continuous latent variable to explicitly model underlying semantics of source sentences and to guide the generation of target translations.In order to perform efficient posterior inference and large-scale training, we build a neural posterior approximator conditioned on both the source and the target sides, and equip it with a reparameterization technique to estimate the variational lower bound.Experiments on both Chinese-English and English-German translation tasks show that the proposed variational neural machine translation achieves significant improvements over the vanilla neural machine translation baselines.

Implicit discourse relation recognition is a crucial component for automatic discourselevel analysis and nature language understanding.Previous studies exploit discriminative models that are built on either powerful manual features or deep discourse representations.In this paper, instead, we explore generative models and propose a variational neural discourse relation recognizer.We refer to this model as VarNDRR.VarNDRR establishes a directed probabilistic model with a latent continuous variable that generates both a discourse and the relation between the two arguments of the discourse.In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound.This allows VarNDRR to be trained with standard stochastic gradient methods.Experiments on the benchmark data set show that VarNDRR can achieve comparable results against stateof-the-art baselines without using any manual features.

Implicit discourse relation recognition remains a serious challenge due to the absence of discourse connectives.In this paper, we propose a Shallow Convolutional Neural Network (SCNN) for implicit discourse relation recognition, which contains only one hidden layer but is effective in relation recognition.The shallow structure alleviates the overfitting problem, while the convolution and nonlinear operations help preserve the recognition and generalization ability of our model.Experiments on the benchmark data set show that our model achieves comparable and even better performance when comparing against current state-of-the-art systems.

Trabecular bone (TB) is a complex quasi-random network of interconnected plates and rods. TB constantly remodels to adapt to the stresses to which it is subjected (Wolff's Law). In osteoporosis, this dynamic equilibrium between bone formation and resorption is perturbed, leading to bone loss and structural deterioration. Both bone loss and structural deterioration increase fracture risk. Bone's mechanical behavior can only be partially explained by variations in bone mineral density, which led to the notion of bone structural quality. Previously, we developed digital topological analysis (DTA) which classifies plates, rods, profiles, edges, and junctions in a TB skeletal representation. Although the method has become quite popular, a major limitation of DTA is that it provides only hard classifications of different topological entities, failing to distinguish between narrow and wide plates. Here, we present a new method called volumetric topological analysis (VTA) for regional quantification of TB topology. At each TB location, the method uniquely classifies its topology on the continuum between perfect plates and perfect rods, facilitating early detections of TB alterations from plates to rods according to the known etiology of osteoporotic bone loss. Several new ideas, including manifold distance transform, manifold scale, and feature propagation have been introduced here and combined with existing DTA and distance transform methods, leading to the new VTA technology. This method has been applied to multidetector computed tomography (CT) and micro-computed tomography ( μCT) images of four cadaveric distal tibia and five distal radius specimens. Both intra- and inter-modality reproducibility of the method has been examined using repeat CT and μCT scans of distal tibia specimens. Also, the method's ability to predict experimental biomechanical properties of TB via CT imaging under in vivo conditions has been quantitatively examined and the results found are very encouraging.