Fundamental problems in robotics involve both discrete variables, like the choice of control modes or gear switching, and continuous variables, like velocity setpoints and control gains. They're often difficult to tackle, because it's not always obvious which algorithms or control policies might best fit. That's why researchers at Google parent company Alphabet's DeepMind recently proposed a technique -- continuous-discrete hybrid learning -- that optimizes for discrete and continuous actions simultaneously, treating hybrid problems in their native form. A paper published on the preprint server Arxiv.org "Many state-of-the-art … approaches have been optimized to work well with either discrete or continuous action spaces but can rarely handle both … or perform better in one parameterization than another," the coauthors wrote.

Fundamental problems in robotics involve both discrete variables, like the choice of control modes or gear switching, and continuous variables, like velocity setpoints and control gains. They're often difficult to tackle, because it's not always obvious which algorithms or control policies might best fit. That's why researchers at Google parent company Alphabet's DeepMind recently proposed a technique -- continuous-discrete hybrid learning -- that optimizes for discrete and continuous actions simultaneously, treating hybrid problems in their native form. A paper published on the preprint server Arxiv.org "Many state-of-the-art … approaches have been optimized to work well with either discrete or continuous action spaces but can rarely handle both … or perform better in one parameterization than another," the coauthors wrote.

Analyzing biopsied tissue samples for signs of malignant growth is a crucial part of cancer diagnosis. But many places around the country suffer from a lack of neuropathologists, which prevents these fundamental procedures from happening in a timely manner. Recent studies have warned of a "pathologist gap" which may grow through 2030. Scientists have demonstrated an A.I. not only capable of completing such procedures in less than three minutes, but can do so more accurately than a human. Of the 15.2 million people around the world diagnosed annually with some form of cancer, nearly 80 percent will undergo biopsy surgery to remove and test a piece of the tumor. In the case of brain tumors, which this new study focused on, the testing process can take up to 30 minutes (if there's a neuropathologist on hand to conduct the test) and requires time and labor-intensive freezing, thawing and chemical staining of samples in order to make a diagnosis.

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes. In this paper, we propose a generative latent variable model, called SPACE, that provides a unified probabilistic modeling framework that combines the best of spatial-attention and scene-mixture approaches. SPACE can explicitly provide factorized object representations for foreground objects while also decomposing background segments of complex morphology. Previous models are good at either of these, but not both. SPACE also resolves the scalability problems of previous methods by incorporating parallel spatial-attention and thus is applicable to scenes with a large number of objects without performance degradations. We show through experiments on Atari and 3D-Rooms that SPACE achieves the above properties consistently in comparison to SPAIR, IODINE, and GENESIS. Results of our experiments can be found on our project website: https://sites.google.com/view/space-project-page

Low-power sensing technologies, such as wearables, have emerged in the healthcare domain since they enable continuous and non-invasive monitoring of physiological signals. In order to endow such devices with clinical value, classical signal processing has encountered numerous challenges. However, data-driven methods, such as machine learning, offer attractive accuracies at the expense of being resource and memory demanding. In this paper, we focus on the inference of neural networks running in microcontrollers and low-power processors which wearable sensors and devices are generally equipped with. In particular, we adapted an existing convolutional-recurrent neural network, designed to detect and classify cardiac arrhythmias from a single-lead electrocardiogram, to the low-power embedded System-on-Chip nRF52 from Nordic Semiconductor with an ARM's Cortex-M4 processing core. We show our implementation in fixed-point precision, using the CMSIS-NN libraries, yields a drop of $F_1$ score from 0.8 to 0.784, from the original implementation, with a memory footprint of 195.6KB, and a throughput of 33.98MOps/s.

Click-through rate (CTR) prediction is an essential task in industrial applications such as video recommendation. Recently, deep learning models have been proposed to learn the representation of users' overall interests, while ignoring the fact that interests may dynamically change over time. We argue that it is necessary to consider the continuous-time information in CTR models to track user interest trend from rich historical behaviors. In this paper, we propose a novel Deep Time-Stream framework (DTS) which introduces the time information by an ordinary differential equations (ODE). DTS continuously models the evolution of interests using a neural network, and thus is able to tackle the challenge of dynamically representing users' interests based on their historical behaviors. In addition, our framework can be seamlessly applied to any existing deep CTR models by leveraging the additional Time-Stream Module, while no changes are made to the original CTR models. Experiments on public dataset as well as real industry dataset with billions of samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with existing methods.

Batch Normalization (BN) techniques have been proposed to reduce the so-called Internal Covariate Shift (ICS) by attempting to keep the distributions of layer outputs unchanged. Experiments have shown their effectiveness on training deep neural networks. However, since only the first two moments are controlled in these BN techniques, it seems that a weak constraint is imposed on layer distributions and furthermore whether such constraint can reduce ICS is unknown. Thus this paper proposes a measure for ICS by using the Earth Mover (EM) distance and then derives the upper and lower bounds for the measure to provide a theoretical analysis of BN. The upper bound has shown that BN techniques can control ICS only for the outputs with low dimensions and small noise whereas their control is NOT effective in other cases. This paper also proves that such control is just a bounding of ICS rather than a reduction of ICS. Meanwhile, the analysis shows that the high-order moments and noise, which BN cannot control, have great impact on the lower bound. Based on such analysis, this paper furthermore proposes an algorithm that unitizes the outputs with an adjustable parameter to further bound ICS in order to cope with the problems of BN. The upper bound for the proposed unitization is noise-free and only dominated by the parameter. Thus, the parameter can be trained to tune the bound and further to control ICS. Besides, the unitization is embedded into the framework of BN to reduce the information loss. The experiments show that this proposed algorithm outperforms existing BN techniques on CIFAR-10, CIFAR-100 and ImageNet datasets.

Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution, which captures the intrinsic randomness of the long term rewards. Most of the existing literature on DRL focuses on problems with discrete action space and value based methods. In this work, motivated by applications in robotics with continuous action space control settings, we propose sample-based distributional policy gradient (SDPG) algorithm. It models the return distribution using samples via a reparameterization technique widely used in generative modeling and inference. We compare SDPG with the state-of-art policy gradient method in DRL, distributed distributional deterministic policy gradients (D4PG), which has demonstrated state-of-art performance. We apply SDPG and D4PG to multiple OpenAI Gym environments and observe that our algorithm shows better sample efficiency as well as higher reward for most tasks.

In transmission X-ray microscopy (TXM) systems, the rotation of a scanned sample might be restricted to a limited angular range to avoid collision to other system parts or high attenuation at certain tilting angles. Image reconstruction from such limited angle data suffers from artifacts due to missing data. In this work, deep learning is applied to limited angle reconstruction in TXMs for the first time. With the challenge to obtain sufficient real data for training, training a deep neural network from synthetic data is investigated. Particularly, the U-Net, the state-of-the-art neural network in biomedical imaging, is trained from synthetic ellipsoid data and multi-category data to reduce artifacts in filtered back-projection (FBP) reconstruction images. The proposed method is evaluated on synthetic data and real scanned chlorella data in $100^\circ$ limited angle tomography. For synthetic test data, the U-Net significantly reduces root-mean-square error (RMSE) from $2.55 \times 10^{-3}$ {\mu}m$^{-1}$ in the FBP reconstruction to $1.21 \times 10^{-3}$ {\mu}m$^{-1}$ in the U-Net reconstruction, and also improves structural similarity (SSIM) index from 0.625 to 0.920. With penalized weighted least square denoising of measured projections, the RMSE and SSIM are further improved to $1.16 \times 10^{-3}$ {\mu}m$^{-1}$ and 0.932, respectively. For real test data, the proposed method remarkably improves the 3-D visualization of the subcellular structures in the chlorella cell, which indicates its important value for nano-scale imaging in biology, nanoscience and materials science.

Transfer learning --- transferring learned knowledge --- has brought a paradigm shift in the way models are trained. The lucrative benefits of improved accuracy and reduced training time have shown promise in training models with constrained computational resources and fewer training samples. Specifically, publicly available text-based models such as GloVe and BERT that are trained on large corpus of datasets have seen ubiquitous adoption in practice. In this paper, we ask, "can transfer learning in text prediction models be exploited to perform misclassification attacks?" As our main contribution, we present novel attack techniques that utilize unintended features learnt in the teacher (public) model to generate adversarial examples for student (downstream) models. To the best of our knowledge, ours is the first work to show that transfer learning from state-of-the-art word-based and sentence-based teacher models increase the susceptibility of student models to misclassification attacks. First, we propose a novel word-score based attack algorithm for generating adversarial examples against student models trained using context-free word-level embedding model. On binary classification tasks trained using the GloVe teacher model, we achieve an average attack accuracy of 97% for the IMDB Movie Reviews and 80% for the Fake News Detection. For multi-class tasks, we divide the Newsgroup dataset into 6 and 20 classes and achieve an average attack accuracy of 75% and 41% respectively. Next, we present length-based and sentence-based misclassification attacks for the Fake News Detection task trained using a context-aware BERT model and achieve 78% and 39% attack accuracy respectively. Thus, our results motivate the need for designing training techniques that are robust to unintended feature learning, specifically for transfer learned models.