Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves candidate items relevant to user interests, while the ranking stage sorts candidate items by user interests. Thus, the most critical ability is to model and represent user interests for either stage. Most of the existing deep learning-based models represent one user as a single vector which is insufficient to capture the varying nature of user's interests. In this paper, we approach this problem from a different view, to represent one user with multiple vectors encoding the different aspects of the user's interests. We propose the Multi-Interest Network with Dynamic routing (MIND) for dealing with user's diverse interests in the matching stage. Specifically, we design a multi-interest extractor layer based on capsule routing mechanism, which is applicable for clustering historical behaviors and extracting diverse interests. Furthermore, we develop a technique named label-aware attention to help learn a user representation with multiple vectors. Through extensive experiments on several public benchmarks and one large-scale industrial dataset from Tmall, we demonstrate that MIND can achieve superior performance than state-of-the-art methods for recommendation. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.

We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs. The approach learns an encoding of the samples in the training corpus using an unsupervised variational autoencoder-decoder architecture, without the need for an explicit parametric representation of the original designs. To facilitate the generation of smooth final surfaces, we develop a 3D shape representation based on a distance transformation of the original 3D data, rather than using the commonly utilized binary voxel representation. Once established, the generator maps the latent space representations to the high-dimensional distance transformation fields, which are then automatically surfaced to produce 3D representations amenable to physics simulations or other objective function evaluation modules. We demonstrate our approach for the computational design of gliders that are optimized to attain prescribed performance scores. Our results show that when combined with genetic optimization, the proposed approach can generate a rich set of candidate concept designs that achieve prescribed functional goals, even when the original dataset has only a few or no solutions that achieve these goals.

The combination of deep neural network models and reinforcement learning algorithms can make it possible to learn policies for robotic behaviors that directly read in raw sensory inputs, such as camera images, effectively subsuming both estimation and control into one model. However, real-world applications of reinforcement learning must specify the goal of the task by means of a manually programmed reward function, which in practice requires either designing the very same perception pipeline that end-to-end reinforcement learning promises to avoid, or else instrumenting the environment with additional sensors to determine if the task has been performed successfully. In this paper, we propose an approach for removing the need for manual engineering of reward specifications by enabling a robot to learn from a modest number of examples of successful outcomes, followed by actively solicited queries, where the robot shows the user a state and asks for a label to determine whether that state represents successful completion of the task. While requesting labels for every single state would amount to asking the user to manually provide the reward signal, our method requires labels for only a tiny fraction of the states seen during training, making it an efficient and practical approach for learning skills without manually engineered rewards. We evaluate our method on real-world robotic manipulation tasks where the observations consist of images viewed by the robot's camera. In our experiments, our method effectively learns to arrange objects, place books, and drape cloth, directly from images and without any manually specified reward functions, and with only 1-4 hours of interaction with the real world.

In the past two years, over 30 papers have proposed to use convolutional neural network (CNN) for AD classification. However, the classification performances across studies are difficult to compare. Moreover, these studies are hardly reproducible because their frameworks are not publicly accessible. Lastly, some of these papers may reported biased performances due to inadequate or unclear validation procedure and also it is unclear how the model architecture and parameters were chosen. In the present work, we aim to address these limitations through three main contributions. First, we performed a systematic literature review of studies using CNN for AD classification from anatomical MRI. We identified four main types of approaches: 2D slice-level, 3D patch-level, ROI-based and 3D subject-level CNN. Moreover, we found that more than half of the surveyed papers may have suffered from data leakage and thus reported biased performances. Our second contribution is an open-source framework for classification of AD. Thirdly, we used this framework to rigorously compare different CNN architectures, which are representative of the existing literature, and to study the influence of key components on classification performances. On the validation set, the ROI-based (hippocampus) CNN achieved highest balanced accuracy (0.86 for AD vs CN and 0.80 for sMCI vs pMCI) compared to other approaches. Transfer learning with autoencoder pre-training did not improve the average accuracy but reduced the variance. Training using longitudinal data resulted in similar or higher performance, depending on the approach, compared to training with only baseline data. Sophisticated image preprocessing did not improve the results. Lastly, CNN performed similarly to standard SVM for task AD vs CN but outperformed SVM for task sMCI vs pMCI, demonstrating the potential of deep learning for challenging diagnostic tasks.

Predicting unscheduled breakdowns of plasma etching equipment can reduce maintenance costs and production losses in the semiconductor industry. However, plasma etching is a complex procedure and it is hard to capture all relevant equipment properties and behaviors in a single physical model. Machine learning offers an alternative for predicting upcoming machine failures based on relevant data points. In this paper, we describe three different machine learning tasks that can be used for that purpose: (i) predicting Time-To-Failure (TTF), (ii) predicting health state, and (iii) predicting TTF intervals of an equipment. Our results show that trained machine learning models can outperform benchmarks resembling human judgments in all three tasks. This suggests that machine learning offers a viable alternative to currently deployed plasma etching equipment maintenance strategies and decision making processes.

We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only partly successful and is able to better capture the underlying clean signal than the noise, the output of the network helps to disentangle the clean audio from the rest of the signal. The method is completely unsupervised and only trains on the specific audio clip that is being denoised. Our experiments demonstrate favorable performance in comparison to the literature methods, and our code and audio samples are available at https: //github.com/mosheman5/DNP. Index Terms: Audio denoising; Unsupervised learning

Mental disorders such as Autism Spectrum Disorders (ASD) are heterogeneous disorders that are notoriously difficult to diagnose, especially in children. The current psychiatric diagnostic process is based purely on the behavioural observation of symptomology (DSM-5/ICD-10) and may be prone to over-prescribing of drugs due to misdiagnosis. In order to move the field towards more quantitative fashion, we need advanced and scalable machine learning infrastructure that will allow us to identify reliable biomarkers of mental health disorders. In this paper, we propose a framework called ASD-DiagNet for classifying subjects with ASD from healthy subjects by using only fMRI data. We designed and implemented a joint learning procedure using an autoencoder and a single layer perceptron which results in improved quality of extracted features and optimized parameters for the model. Further, we designed and implemented a data augmentation strategy, based on linear interpolation on available feature vectors, that allows us to produce synthetic datasets needed for training of machine learning models. The proposed approach is evaluated on a public dataset provided by Autism Brain Imaging Data Exchange including 1035 subjects coming from 17 different brain imaging centers. Our machine learning model outperforms other state of the art methods from 13 imaging centers with increase in classification accuracy up to 20% with maximum accuracy of 80%. The machine learning technique presented in this paper, in addition to yielding better quality, gives enormous advantages in terms of execution time (40 minutes vs. 6 hours on other methods). The implemented code is available as GPL license on GitHub portal of our lab (https://github.com/pcdslab/ASD-DiagNet).

Yeqi Liu, Chuanyang Gong, Ling Yang, Yingyi Chen * Abstract Long-term prediction of multivariate time series is still an important but challenging problem. The key to solve this problem is to capture the spatial correlations at the same time, the spatiotemporal relationships at different times and the long-term dependence of the temporal relationships between different series. Attention-based recurrent neural networks (RNN) can effectively represent the dynamic spatiotemporal relationships between exogenous series and target series, but it only performs well in one-step time prediction and short-term time prediction. The first phase produces violent but decentralized response weight, while the second phase leads to stationary and concentrated response weight. Secondly, we employ multiple attentions on target series to boost the long-term dependence. Finally, we study the performance of deep spatial attention mechanism and provide experiment and interpretation. Our methods outperform nine baseline methods on four datasets in the fields of energy, finance, environment and medicine, respectively. Keywords: Time series prediction; Spatiotemporal relationship; Attention mechanism; Dual-stage two-phase model; Deep attention network. 1 Introduction Recent developments in the Internet of Things and Big Data have led to the continuous expansion of data scale(Le & Ge, 2019). Hence, the long-term prediction of multivariate time series has more practical significance, e.g., it is more significant to forecast the weather of one or more days than to forecast the weather of the next hour in the future. However, the long-term prediction of multivariate time series is still a challenging problem, which is mainly reflected in the feature representation and selection mechanism of spatiotemporal relationships between different series.

Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers. However, such model suffers from the limitation that it can only convert the voice to the speakers in the training data, which narrows down the applicable scenario of VC. In this paper, we proposed a novel one-shot VC approach which is able to perform VC by only an example utterance from source and target speaker respectively, and the source and target speaker do not even need to be seen during training. This is achieved by disentangling speaker and content representations with instance normalization (IN). Objective and subjective evaluation shows that our model is able to generate the voice similar to target speaker. In addition to the performance measurement, we also demonstrate that this model is able to learn meaningful speaker representations without any supervision.

Majority of state-of-the-art deep learning methods for vision applications are discriminative approaches, which model the conditional distribution. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and is able to generate high quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarily-labeled data.