Designing accurate and efficient CNNs for mobile devices is challenging due to the large design space and expensive computational methods. Although many mobile CNNs are available for developers to train and deploy to mobile devices, existing CNN architecture may not be able to achieve the best results for some tasks on mobile devices. Last year, Google introduced an automated mobile neural architecture search (MNAS) approach, and proposed MnasNet based on reinforcement learning to automatically design mobile models. Facebook then proposed FBNet, a differentiable neural architecture search (DNAS) framework to optimize CNN architecture based on a gradient method. Both FBNet and MnasNet introduced automated solutions to change the way deep learning models are designed for mobile.

If you are dealing with Statistics, Data Science, Machine Learning, Artificial Intelligence or even general Computer Science, Mathematics, Engineering or Physics, you've probably come across the term Entropy more than once. Entropy is a significant, widely used and above all successful measure for quantifying inhomogeneity, impurity, complexity and uncertainty or unpredictability. The concept of entropy is more than 200 years old, and still, or perhaps because of that, it is an integral part of the latest machine learning models that are successfully deployed on real-world data sets. In this article, I want to highlight the simplicity, beauty and meaning of entropy. Entropy and its special forms are able to achieve a conceptual understanding of the data in an intuitive way--something we should exploit more often.

If you too want to start a career in AI and DL, check out our "PG Certificate Program in Artificial Intelligence & Deep Learning" course http://bit.ly/2F42DeK AI and Deep learning have shown promising growth in recent years and in the near future can change the way companies operate. After completing the Deep Learning and Artificial Intelligence online course, you'll be able to: - Use Tensorflow, Scikit Learn library, Keras and other machine learning and deep learning tools.

Spatial studies of transcriptome provide biologists with gene expression maps of heterogeneous and complex tissues. However, most experimental protocols for spatial transcriptomics suffer from the need to select beforehand a small fraction of genes to be quantified over the entire transcriptome. Standard single-cell RNA sequencing (scRNA-seq) is more prevalent, easier to implement and can in principle capture any gene but cannot recover the spatial location of the cells. In this manuscript, we focus on the problem of imputation of missing genes in spatial transcriptomic data based on (unpaired) standard scRNA-seq data from the same biological tissue. Building upon domain adaptation work, we propose gimVI, a deep generative model for the integration of spatial transcriptomic data and scRNA-seq data that can be used to impute missing genes. After describing our generative model and an inference procedure for it, we compare gimVI to alternative methods from computational biology or domain adaptation on real datasets and outperform Seurat Anchors, Liger and CORAL to impute held-out genes.

The pervasive brittleness of deep neural networks [Sze 14; Eng 19; HD19; Ath 18] has attracted significant attention in recent years. Particularly worrisome is the phenomenon of adversarial examples [Big 13; Sze 14], imperceptibly perturbed natural inputs that induce erroneous predictions in state-of-the-art classifiers. Previous work has proposed a variety of explanations for this phenomenon, ranging from theoretical models [Sch 18; BPR18] to arguments based on concentration of measure in high-dimensions [Gil 18; MDM18; Sha 19a]. These theories, however, are often unable to fully capture behaviors we observe in practice (we discuss this further in Section 5). More broadly, previous work in the field tends to view adversarial examples as aberrations arising either from the high dimensional nature of the input space or statistical fluctuations in the training data [Sze 14; GSS15; Gil 18]. From this point of view, it is natural to treat adversarial robustness as a goal that can be disentangled and pursued independently from maximizing accuracy [Mad 18; SHS19; Sug 19], either through improved standard regularization methods [TG16] or pre/post-processing of network inputs/outputs [Ues 18; CW17a; He 17].

Recommending appropriate items to users is crucial in many e-commerce platforms that contain implicit data as users' browsing, purchasing and streaming history. One common approach consists in selecting the N most relevant items to each user, for a given N, which is called top-N recommendation. To do so, recommender systems rely on various kinds of information, like item and user features, past interest of users for items, browsing history and trust between users. However, they often use only one or two such pieces of information, which limits their performance. In this paper, we design and implement GraFC2T2, a general graph-based framework to easily combine and compare various kinds of side information for top-N recommendation. It encodes content-based features, temporal and trust information into a complex graph, and uses personalized PageRank on this graph to perform recommendation. We conduct experiments on Epinions and Ciao datasets, and compare obtained performances using F1-score, Hit ratio and MAP evaluation metrics, to systems based on matrix factorization and deep learning. This shows that our framework is convenient for such explorations, and that combining different kinds of information indeed improves recommendation in general.

Multi-domain image-to-image translation is a problem where the goal is to learn mappings among multiple domains. This problem is challenging in terms of scalability because it requires the learning of numerous mappings, the number of which increases proportional to the number of domains. However, generative adversarial networks (GANs) have emerged recently as a powerful framework for this problem. In particular, label-conditional extensions (e.g., StarGAN) have become a promising solution owing to their ability to address this problem using only a single unified model. Nonetheless, a limitation is that they rely on the availability of large-scale clean-labeled data, which are often laborious or impractical to collect in a real-world scenario. To overcome this limitation, we propose a novel model called the label-noise robust image-to-image translation model (RMIT) that can learn a clean label conditional generator even when noisy labeled data are only available. In particular, we propose a novel loss called the virtual cycle consistency loss that is able to regularize cyclic reconstruction independently of noisy labeled data, as well as we introduce advanced techniques to boost the performance in practice. Our experimental results demonstrate that RMIT is useful for obtaining label-noise robustness in various settings including synthetic and real-world noise.

In e-commerce, product content, especially product images have a significant influence on a customer's journey from product discovery to evaluation and finally, purchase decision. Since many e-commerce retailers sell items from other third-party marketplace sellers besides their own, the content published by both internal and external content creators needs to be monitored and enriched, wherever possible. Despite guidelines and warnings, product listings that contain offensive and non-compliant images continue to enter catalogs. Offensive and non-compliant content can include a wide range of objects, logos, and banners conveying violent, sexually explicit, racist, or promotional messages. Such images can severely damage the customer experience, lead to legal issues, and erode the company brand. In this paper, we present a machine learning driven offensive and non-compliant image detection system for extremely large e-commerce catalogs. This system proactively detects and removes such content before they are published to the customer-facing website. This paper delves into the unique challenges of applying machine learning to real-world data from retail domain with hundreds of millions of product images. We demonstrate how we resolve the issue of non-compliant content that appears across tens of thousands of product categories. We also describe how we deal with the sheer variety in which each single non-compliant scenario appears. This paper showcases a number of practical yet unique approaches such as representative training data creation that are critical to solve an extremely rarely occurring problem. In summary, our system combines state-of-the-art image classification and object detection techniques, and fine tunes them with internal data to develop a solution customized for a massive, diverse, and constantly evolving product catalog.

In this paper, we present a deep learning-based (DL-based) algorithm, as a purely mathematical platform, for providing intuitive understanding of the properties of electromagnetic (EM) wave-matter interaction in nanostructures. This approach is based on using the dimensionality reduction (DR) technique to significantly reduce the dimensionality of a generic EM wave-matter interaction problem without imposing significant error. Such an approach implicitly provides useful information about the role of different features (or design parameters such as geometry) of the nanostructure in its response functionality. To demonstrate the practical capabilities of this DL-based technique, we apply it to a reconfigurable optical metadevice enabling dual-band and triple-band optical absorption in the telecommunication window. Combination of the proposed approach with existing commercialized full-wave simulation tools offers a powerful toolkit to extract basic mechanisms of wave-matter interaction in complex EM devices and facilitate the design and optimization of nanostructures for a large range of applications including imaging, spectroscopy, and signal processing. It is worth to mention that the demonstrated approach is general and can be used in a large range of problems as long as enough training data can be provided.

Extreme multi-label classification (XMC) aims to assign to an instance the most relevant subset of labels from a colossal label set. Due to modern applications that lead to massive label sets, the scalability of XMC has attracted much recent attention from both academia and industry. In this paper, we establish a three-stage framework to solve XMC efficiently, which includes 1) indexing the labels, 2) matching the instance to the relevant indices, and 3) ranking the labels from the relevant indices. This framework unifies many existing XMC approaches. Based on this framework, we propose a modular deep learning approach SLINMER: Semantic Label Indexing, Neural Matching, and Efficient Ranking. The label indexing stage of SLINMER can adopt different semantic label representations leading to different configurations of SLINMER. Empirically, we demonstrate that several individual configurations of SLINMER achieve superior performance than the state-of-the-art XMC approaches on several benchmark datasets. Moreover, by ensembling those configurations, SLINMER can achieve even better results. In particular, on a Wiki dataset with around 0.5 millions of labels, the precision@1 is increased from 61% to 67%.