Stock market volatility forecasting is a task relevant to assessing market risk. We investigate the interaction between news and prices for the one-day-ahead volatility prediction using state-of-the-art deep learning approaches. The proposed models are trained either end-to-end or using sentence encoders transfered from other tasks. We evaluate a broad range of stock market sectors, namely Consumer Staples, Energy, Utilities, Heathcare, and Financials. Our experimental results show that adding news improves the volatility forecasting as compared to the mainstream models that rely only on price data. In particular, our model outperforms the widely-recognized GARCH(1,1) model for all sectors in terms of coefficient of determination $R^2$, $MSE$ and $MAE$, achieving the best performance when training from both news and price data.

We design a dispatch system to improve the peak service quality of video on demand (VOD). Our system predicts the hot videos during the peak hours of the next day based on the historical requests, and dispatches to the content delivery networks (CDNs) at the previous off-peak time. In order to scale to billions of videos, we build the system with two neural networks, one for video clustering and the other for dispatch policy developing. The clustering network employs autoencoder layers and reduces the video number to a fixed value. The policy network employs fully connected layers and ranks the clustered videos with dispatch probabilities. The two networks are coupled with weight-sharing temporal layers, which analyze the video request sequences with convolutional and recurrent modules. Therefore, the clustering and dispatch tasks are trained in an end-to-end mechanism. The real-world results show that our approach achieves an average prediction accuracy of 17%, compared with 3% from the present baseline method, for the same amount of dispatches.

Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. Collecting and publishing a dataset in this environment can cause concerns over privacy of the individuals in the dataset. In this paper we examine these privacy concerns. In particular, given a target application, how can we mask sensitive attributes in the data while preserving the utility of the data in that target application. Our focus is on protecting attributes that are hidden and can be inferred from the data by machine learning algorithms. We propose a generic framework that (1) removes the knowledge useful for inferring sensitive information, but (2) preserves the knowledge relevant to a given target application. We use deep neural networks and generative adversarial networks (GAN) to create privacy-preserving perturbations. Our noise-generating network is compact and efficient for running on mobile devices. Through extensive experiments, we show that our method outperforms conventional methods in effectively hiding the sensitive attributes while guaranteeing high performance for the target application. Our results hold for new neural network architectures, not seen before during training and are suitable for training new classifiers.

Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defines a soft decision tree where leaves correspond to experts and decision nodes correspond to gating models that softly choose between its children, and as such, the model defines a soft hierarchical partitioning of the input space. In this work, we propose a variant of dropout for hierarchical mixture of experts that is faithful to the tree hierarchy defined by the model, as opposed to having a flat, unitwise independent application of dropout as one has with multi-layer perceptrons. We show that on a synthetic regression data and on MNIST and CIFAR-10 datasets, our proposed dropout mechanism prevents overfitting on trees with many levels improving generalization and providing smoother fits.

We prove that the binary classifiers of bit strings generated by random wide deep neural networks are biased towards simple functions. The simplicity is captured by the following two properties. For any given input bit string, the average Hamming distance of the closest input bit string with a different classification is at least $\sqrt{n\left/\left(2\pi\ln n\right)\right.}$, where $n$ is the length of the string. Moreover, if the bits of the initial string are flipped randomly, the average number of flips required to change the classification grows linearly with $n$. On the contrary, for a uniformly random binary classifier, the average Hamming distance of the closest input bit string with a different classification is one, and the average number of random flips required to change the classification is two. These results are confirmed by numerical experiments on deep neural networks with two hidden layers, and settle the conjecture stating that random deep neural networks are biased towards simple functions. The conjecture that random deep neural networks are biased towards simple functions was proposed and numerically explored in [Valle P\'erez et al., arXiv:1805.08522] to explain the unreasonably good generalization properties of deep learning algorithms. By providing a precise characterization of the form of this bias towards simplicity, our results open the way to a rigorous proof of the generalization properties of deep learning algorithms in real-world scenarios.

As fas as we are aware, using sequence to sequence algorithms for query expansion hasnot been explored yet in Information Retrievalliterature nor in Question-Answering's. We tried to fill this gap in the literature with a custom Query Expansion system trained and tested on open datasets. One specificity of our engine compared to classic ones is that it does not need the documents to expand the introduced query. We test our expansions on three different tasks: Information Retrieval, Answer preselection and Text classification. Our method yielded a slight improvement in performance in the three tasks .

Deep neural networks have demonstrated cutting edge performance on various tasks including classification. However, it is well known that adversarially designed imperceptible perturbation of the input can mislead advanced classifiers. In this paper, Permutation Phase Defense (PPD), is proposed as a novel method to resist adversarial attacks. PPD combines random permutation of the image with phase component of its Fourier transform. The basic idea behind this approach is to turn adversarial defense problems analogously into symmetric cryptography, which relies solely on safekeeping of the keys for security. In PPD, safe keeping of the selected permutation ensures effectiveness against adversarial attacks. Testing PPD on MNIST and CIFAR-10 datasets yielded state-of-the-art robustness against the most powerful adversarial attacks currently available.

This is Part 1 of Breaking the curse of small datasets in Machine Learning. In this part, I will discuss how the size of the data set impacts traditional Machine Learning algorithms and few ways to mitigate these issues. In Part 2, I will discuss how deep learning model performance depends on data size and how to work with smaller data sets to get similar performances. We all are aware of how machine learning has revolutionized our world in recent years and has made a variety of complex tasks much easier to perform. The recent breakthroughs in implementing Deep learning techniques has shown that superior algorithms and complex architectures can impart human-like abilities to machines for specific tasks.

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this paradigm to universal complex tasks. Among them, the low efficiency of data utilization in model-free reinforcement algorithms is of great concern. In contrast, the model-based reinforcement learning algorithms can reveal underlying dynamics in learning environments and seldom suffer the data utilization problem. To address the problem, a model-based reinforcement learning algorithm with attention mechanism embedded is proposed as an extension of World Models in this paper. We learn the environment model through Mixture Density Network Recurrent Network(MDN-RNN) for agents to interact, with combinations of variational auto-encoder(VAE) and attention incorporated in state value estimates during the process of learning policy. In this way, agent can learn optimal policies through less interactions with actual environment, and final experiments demonstrate the effectiveness of our model in control problem.

Twitter has been a prominent social media platform for mining population-level health data and accurate clustering of health-related tweets into topics is important for extracting relevant health insights. In this work, we propose deep convolutional autoencoders for learning compact representations of health-related tweets, further to be employed in clustering. We compare our method to several conventional tweet representation methods including bag-of-words, term frequency-inverse document frequency, Latent Dirichlet Allocation and Non-negative Matrix Factorization with 3 different clustering algorithms. Our results show that the clustering performance using proposed representation learning scheme significantly outperforms that of conventional methods for all experiments of different number of clusters. In addition, we propose a constraint on the learned representations during the neural network training in order to further enhance the clustering performance. All in all, this study introduces utilization of deep neural network-based architectures, i.e., deep convolutional autoencoders, for learning informative representations of health-related tweets.