Super Resolution is the process of recovering a High Resolution (HR) image from a given Low Resolution (LR) image. An image may have a "lower resolution" due to a smaller spatial resolution (i.e. Clearly, on applying a degradation function, we obtain the LR image from the HR image. But, can we do the inverse? If we know the exact degradation function, by applying its inverse to the LR image, we can recover the HR image.

Data augmentation (DA) has been widely utilized to improve generalization in training deep neural networks. Recently, human-designed data augmentation has been gradually replaced by automatically learned augmentation policy. Through finding the best policy in well-designed search space of data augmentation, AutoAugment can significantly improve validation accuracy on image classification tasks. However, this approach is not computationally practical for large-scale problems. In this paper, we develop an adversarial method to arrive at a computationally-affordable solution called Adversarial AutoAugment, which can simultaneously optimize target related object and augmentation policy search loss. The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization. In contrast to prior work, we reuse the computation in target network training for policy evaluation, and dispense with the retraining of the target network. Compared to AutoAugment, this leads to about 12x reduction in computing cost and 11x shortening in time overhead on ImageNet. We show experimental results of our approach on CIFAR-10/CIFAR-100, ImageNet, and demonstrate significant performance improvements over state-of-the-art. On CIFAR-10, we achieve a top-1 test error of 1.36%, which is the currently best performing single model. On ImageNet, we achieve a leading performance of top-1 accuracy 79.40% on ResNet-50 and 80.00% on ResNet-50-D without extra data.

--Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be reduced at the cost of reduced reliability. A training algorithm is proposed to optimize the reliability of the storage separately for each layer of the network, while incurring a negligible complexity overhead compared to a conventional stochastic gradient descent training. For an exponential energy-reliability model, the proposed training approach can decrease the memory energy consumption of a DNN with binary parameters by 3.3 at isoaccuracy, compared to a reliable implementation. I NTRODUCTION Deep learning [1] has attracted a lot of interest since 2012 and AlexNet's achievements on ImageNet [2], sparking a rapid improvement of the state-of-the-art in diverse fields. However the tradeoff for such results is an antagonizing growth in resource requirements.

Diffractive deep neural network (DNNet) is a novel machine learning framework on the modulation of optical transmission. Diffractive network would get predictions at the speed of light. It's pure passive architecture, no additional power consumption. We improved the accuracy of diffractive network with optical waves at different frequency. Each layers have multiple frequency-channels (optical distributions at different frequency). These channels are merged at the output plane to get final output. The experiment in the fasion-MNIST and EMNIST datasets showed multiple frequency-channels would increase the accuracy a lot. We also give detailed analysis to show the difference between DNNet and MLP. The modulation process in DNNet is actually optical activation function. We develop an open source package ONNet. The source codes are available at https://github.com/closest-git/ONNet.

Autoencoders are a common building block of Deep Learning architectures, where they are mainly used for representation learning. They have also been successfully used in Collaborative Filtering (CF) recommender systems to predict missing ratings. Unfortunately, like all black box machine learning models, they are unable to explain their outputs. Hence, while predictions from an Autoencoder-based recommender system might be accurate, it might not be clear to the user why a recommendation was generated. In this work, we design an explainable recommendation system using an Autoencoder model whose predictions can be explained using the neighborhood based explanation style. Our preliminary work can be considered to be the first step towards an explainable deep learning architecture based on Autoencoders.

The Hamlyn Centre for Robotic Surgery, Imperial College London, UK 2. Institute of Medical Robotics, Shanghai Jiao Tong University, ChinaAbstract Artificial Intelligence (AI) is gradually changing the practice of surgery with the advanced technological development of imaging, navigation and robotic intervention. In this article, the recent successful and influential applications of AI in surgery are reviewed from preoperative planning and intra-operative guidance to the integration of surgical robots. We end with summarizing the current state, emerging trends and major challenges in the future development of AI in surgery. Keywords: Artificial intelligence, Surgical autonomy, Medical robotics, Deep learning 1. Introduction Advances in surgery have made a significant impact on the management of both acute and chronic diseases, prolonging life and continuously extending the boundary of survival. These advances are underpinned by continuing technological developments in diagnosis, imaging, and surgical instrumentation. Complex surgical navigation and planning are made possible through the use of both pre-and intra-operative imaging techniques such as ultrasound, Computed Tomography (CT), and Magnetic Resonance Imaging Preprint submitted to Frontiers of Medicine January 6, 2020 arXiv:2001.00627v1 Many terminal illnesses have been transformed into clinically manageable chronic lifelong conditions and increasing surgery is focused on the systematic level impact on patients, avoiding isolated surgical treatment or anatomical alteration, with careful consideration of metabolic, haemodynamic and neurohormonal consequences that can influence the quality of life. For recent advances in medicine, AI has played an important role in clinical decision support since the early years of developing the MYCIN system [5]. AI is now increasingly used for risk stratification, genomics, imaging and diagnosis, precision medicine, and drug discovery. The introduction of AI in surgery is more recent and it has a strong root in imaging and navigation, with early techniques focused on feature detection and computer assisted intervention for both preoperative planning and intra-operative guidance. Over the years, supervised algorithms such as active shape models, atlas based methods and statistical classifiers have been developed [1]. With recent successes of AlexNet [6], deep learning methods, especially Deep Con-volutional Neural Network (DCNN) where multiple convolutional layers are cascaded, have enabled automatically learned data-driven descriptors, rather than ad hoc handcrafted features, to be used for image understanding with improved robustness and generalizability.

Emotion recognition from speech is one of the key steps towards emotional intelligence in advanced human-machine interaction. Identifying emotions in human speech requires learning features that are robust and discriminative across diverse domains that differ in terms of language, spontaneity of speech, recording conditions, and types of emotions. This corresponds to a learning scenario in which the joint distributions of features and labels may change substantially across domains. In this paper, we propose a deep architecture that jointly exploits a convolutional network for extracting domain-shared features and a long short-term memory network for classifying emotions using domain-specific features. We use transferable features to enable model adaptation from multiple source domains, given the sparseness of speech emotion data and the fact that target domains are short of labeled data. A comprehensive cross-corpora experiment with diverse speech emotion domains reveals that transferable features provide gains ranging from 4.3% to 18.4% in speech emotion recognition. We evaluate several domain adaptation approaches, and we perform an ablation study to understand which source domains add the most to the overall recognition effectiveness for a given target domain.

Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we cast DML as a simple pairwise binary classification problem that classifies a pair of examples as similar or dissimilar. It identifies the most critical issue in this problem-- imbalanced data pairs. To tackle this issue, we propose a simple and effective framework to sample pairs in a batch of data for updating the model. The key to this framework is to define a robust loss for all pairs over a mini-batch of data, which is formulated by distributionally robust optimization. The flexibility in constructing the uncertainty decision set of the dual variable allows us to recover state-of-the-art complicated losses and also to induce novel variants. Metric Learning aims to learn a metric to measure the distance between examples that captures certain notion of human-defined similarity between examples. Deep metric learning (DML) has emerged as an effective approach for learning a metric by training a deep neural network. Simply speaking, a deep neural network can induce new feature embedding of examples and it is trained in such a way that the Euclidean distance between the induced feature embeddings of two similar examples shall be small and that between the induced feature embeddings of two dissimilar pairs shall be large. DML has been widely used in many tasks such as face recognition (Fan et al. (2017)), image retrieval (Chen & Deng (2019)), and classification (Qian et al. (2015); Li et al. (2019)). However, unlike training a deep neural network by minimizing the classification error, training a deep neural network for metric learning is notoriously more difficult (Qian et al. (2018); Wang et al. (2017)).

Signalized intersections are managed by controllers that assign right of way (green, yellow, and red lights) to non-conflicting directions. Optimizing the actuation policy of such controllers is expected to alleviate traffic congestion and its adverse impact. Given such a safety-critical domain, the affiliated actuation policy is required to be interpretable in a way that can be understood and regulated by a human. This paper presents and analyzes several on-line optimization techniques for tuning interpretable control functions. Although these techniques are defined in a general way, this paper assumes a specific class of interpretable control functions (polynomial functions) for analysis purposes. We show that such an interpretable policy function can be as effective as a deep neural network for approximating an optimized signal actuation policy. We present empirical evidence that supports the use of value-based reinforcement learning for on-line training of the control function. Specifically, we present and study three variants of the Deep Q-learning algorithm that allow the training of an interpretable policy function. Our Deep Regulatable Hardmax Q-learning variant is shown to be particularly effective in optimizing our interpretable actuation policy, resulting in up to 19.4% reduced vehicles delay compared to commonly deployed actuated signal controllers.

Automatic differentiation frameworks are optimized for exactly one thing: computing the average mini-batch gradient. Y et, other quantities such as the variance of the mini-batch gradients or many approximations to the Hessian can, in theory, be computed efficiently, and at the same time as the gradient. While these quantities are of great interest to researchers and practitioners, current deep-learning software does not support their automatic calculation. Manually implementing them is burdensome, inefficient if done na ıvely, and the resulting code is rarely shared. This hampers progress in deep learning, and unnecessarily narrows research to focus on gradient descent and its variants; it also complicates replication studies and comparisons between newly developed methods that require those quantities, to the point of impossibility. Its capabilities are illustrated by benchmark reports for computing additional quantities on deep neural networks, and an example application by testing several recent curvature approximations for optimization. The success of deep learning and the applications it fuels can be traced to the popularization of automatic differentiation frameworks. However, this specialization also has its shortcomings: it assumes the user only wants to compute gradients or, more precisely, the average of gradients across a mini-batch of examples. Other quantities can also be computed with automatic differentiation at a comparable cost or minimal overhead to the gradient backpropagation pass; for example, approximate second-order information or the variance of gradients within the batch. These quantities are valuable to understand the geometry of deep neural networks, for the identification of free parameters, and to push the development of more efficient optimization algorithms. But researchers who want to investigate their use face a chicken-and-egg problem: automatic differentiation tools required to go beyond standard gradient methods are not available, but there is no incentive for their implementation in existing deep-learning software as long as no large portion of the users need it. Second-order methods for deep learning have been continuously investigated for decades (e.g., Becker & Le Cun, 1989; Amari, 1998; Bordes et al., 2009; Martens & Grosse, 2015).