Efficient gradient computation of the Jacobian determinant term is a core problem of the normalizing flow framework. Thus, most proposed flow models either restrict to a function class with easy evaluation of the Jacobian determinant, or an efficient estimator thereof. However, these restrictions limit the performance of such density models, frequently requiring significant depth to reach desired performance levels. In this work, we propose Self Normalizing Flows, a flexible framework for training normalizing flows by replacing expensive terms in the gradient by learned approximate inverses at each layer. This reduces the computational complexity of each layer's exact update from $\mathcal{O}(D^3)$ to $\mathcal{O}(D^2)$, allowing for the training of flow architectures which were otherwise computationally infeasible, while also providing efficient sampling. We show experimentally that such models are remarkably stable and optimize to similar data likelihood values as their exact gradient counterparts, while surpassing the performance of their functionally constrained counterparts.

Wireless communications are often subject to fading conditions. Various models have been proposed to capture the inherent randomness of fading in wireless channels, and conventional model-based receiver methods rely on accurate knowledge of this underlying distribution, which in practice may be complex and intractable. In this work we propose a collaborative neural network-based symbol detection mechanism for downlink fading channels, referred to as FedRec, which is based on the maximum a-posteriori probability (MAP) detector. To facilitate training using a limited number of pilots, while capturing a diverse ensemble of fading realizations, we propose a federated training scheme in which multiple users collaborate to jointly learn a universal data-driven detector. The performance of the resulting FedRec receiver is shown to approach the MAP performance in diverse channel conditions without requiring knowledge of the fading statistics, while inducing a substantially reduced communication overhead in its training procedure compared to training in a centralized fashion.

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leverage target information for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

Haptic guidance in a shared steering assistance system has drawn significant attention in intelligent vehicle fields, owing to its mutual communication ability for vehicle control. By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle. However, current haptic guidance steering systems demonstrate some deficiencies in assisting lane changing. This study explored a new steering interaction method, including the design and evaluation of an intention-based haptic shared steering system. Such an intention-based method can support both lane keeping and lane changing assistance, by detecting a driver lane change intention. By using a deep learning-based method to model a driver decision timing regarding lane crossing, an adaptive gain control method was proposed for realizing a steering control system. An intention consistency method was proposed to detect whether the driver and the system were acting towards the same target trajectories and to accurately capture the driver intention. A driving simulator experiment was conducted to test the system performance. Participants were required to perform six trials with assistive methods and one trial without assistance. The results demonstrated that the supporting system decreased the lane departure risk in the lane keeping tasks and could support a fast and stable lane changing maneuver.

We develop and evaluate a deep learning algorithm to classify multiple catheters on neonatal chest and abdominal radiographs. A convolutional neural network (CNN) was trained using a dataset of 777 neonatal chest and abdominal radiographs, with a split of 81%-9%-10% for training-validation-testing, respectively. We employed ResNet-50 (a CNN), pre-trained on ImageNet. Ground truth labelling was limited to tagging each image to indicate the presence or absence of endotracheal tubes (ETTs), nasogastric tubes (NGTs), and umbilical arterial and venous catheters (UACs, UVCs). The data set included 561 images containing 2 or more catheters, 167 images with only one, and 49 with none. Performance was measured with average precision (AP), calculated from the area under the precision-recall curve. On our test data, the algorithm achieved an overall AP (95% confidence interval) of 0.977 (0.679-0.999) for NGTs, 0.989 (0.751-1.000) for ETTs, 0.979 (0.873-0.997) for UACs, and 0.937 (0.785-0.984) for UVCs. Performance was similar for the set of 58 test images consisting of 2 or more catheters, with an AP of 0.975 (0.255-1.000) for NGTs, 0.997 (0.009-1.000) for ETTs, 0.981 (0.797-0.998) for UACs, and 0.937 (0.689-0.990) for UVCs. Our network thus achieves strong performance in the simultaneous detection of these four catheter types. Radiologists may use such an algorithm as a time-saving mechanism to automate reporting of catheters on radiographs.

We study the problem of learning a robot policy to follow natural language instructions that can be easily extended to reason about new objects. We introduce a few-shot language-conditioned object grounding method trained from augmented reality data that uses exemplars to identify objects and align them to their mentions in instructions. We present a learned map representation that encodes object locations and their instructed use, and construct it from our few-shot grounding output. We integrate this mapping approach into an instruction-following policy, thereby allowing it to reason about previously unseen objects at test-time by simply adding exemplars. We evaluate on the task of learning to map raw observations and instructions to continuous control of a physical quadcopter. Our approach significantly outperforms the prior state of the art in the presence of new objects, even when the prior approach observes all objects during training.

The Conformer-Kernel (CK) model [Mitra et al., 2020] builds upon the Transformer-Kernel (TK) [Hofstätter et al., 2019] architecture, that demonstrated strong competitive performance compared to BERTbased [Devlin et al., 2019] ranking methods, but notably at a fraction of the compute and GPU memory cost, at the TREC 2019 Deep Learning track [Craswell et al., 2020b]. Notwithstanding these strong results, the TK model suffers from two clear deficiencies. Firstly, because the TK model employs stacked Transformers for query and document encoding, it is challenging to incorporate long body text into this model as the GPU memory requirement of Transformers' self-attention layers grows quadratically with respect to input sequence length. So, for example, to increase the limit on the maximum input sequence length by 4 from 128 to 512 we would require 16 more GPU memory for each of the self-attention layers in the model. Considering that documents can contain thousands of terms, this limits the model to inspecting only a subset of the document text which may have negative implications, such as poorer retrieval quality and under-retrieval of longer documents [Hofstätter et al., 2020].

We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular structure is motivated by hypothesizing a sequence of intuitive steps that humans apply when trying to solve such a task. The model first predicts the path the target object would follow without intervention and the path the target object should follow in order to solve the task. Next, it predicts the desired path of the action object and generates the placement of the action object. All components of the model are trained jointly in a supervised way; each component receives its own learning signal but learning signals are also backpropagated through the entire architecture. To evaluate the model we use PHYRE - a benchmark test for goal-driven physical reasoning in 2D mechanics puzzles.

In e-commerce portals, generating answers for product-related questions has become a crucial task. In this paper, we focus on the task of product-aware answer generation, which learns to generate an accurate and complete answer from large-scale unlabeled e-commerce reviews and product attributes. However, safe answer problems pose significant challenges to text generation tasks, and e-commerce question-answering task is no exception. To generate more meaningful answers, in this paper, we propose a novel generative neural model, called the Meaningful Product Answer Generator (MPAG), which alleviates the safe answer problem by taking product reviews, product attributes, and a prototype answer into consideration. Product reviews and product attributes are used to provide meaningful content, while the prototype answer can yield a more diverse answer pattern. To this end, we propose a novel answer generator with a review reasoning module and a prototype answer reader. Our key idea is to obtain the correct question-aware information from a large scale collection of reviews and learn how to write a coherent and meaningful answer from an existing prototype answer. To be more specific, we propose a read-and-write memory consisting of selective writing units to conduct reasoning among these reviews. We then employ a prototype reader consisting of comprehensive matching to extract the answer skeleton from the prototype answer. Finally, we propose an answer editor to generate the final answer by taking the question and the above parts as input. Conducted on a real-world dataset collected from an e-commerce platform, extensive experimental results show that our model achieves state-of-the-art performance in terms of both automatic metrics and human evaluations. Human evaluation also demonstrates that our model can consistently generate specific and proper answers.

Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the neural networks trained with noisy labels. Here we propose a novel approach with strong theoretical guarantees for robust training of deep networks trained with noisy labels. The key idea behind our method is to select weighted subsets (coresets) of clean data points that provide an approximately low-rank Jacobian matrix. We then prove that gradient descent applied to the subsets do not overfit the noisy labels. Our extensive experiments corroborate our theory and demonstrate that deep networks trained on our subsets achieve a significantly superior performance compared to state-of-the art, e.g., 6% increase in accuracy on CIFAR-10 with 80% noisy labels, and 7% increase in accuracy on mini Webvision.