Algorithms based on machine learning and deep learning, intended for use in diagnostic imaging, are moving into the commercial pipeline. However, providers will have to overcome multiple challenges to incorporate these tools into daily clinical workflows in radiology. There now are numerous algorithms in various stages of development and in the FDA approval process, and experts believe that there could eventually be hundreds or even thousands of AI-based apps to improve the quality and efficiency of radiology. The emerging applications based on machine learning and deep learning primarily involve algorithms to automate such processes in radiology as detecting abnormal structures in images, such as cancerous lesions and nodules. The technology can be used on a variety of modalities, such as CT scans and X-rays.

AI promises considerable economic benefits, even as it disrupts the world of work. These three priorities will help achieve good outcomes. The time may have finally come for artificial intelligence (AI) after periods of hype followed by several "AI winters" over the past 60 years. AI now powers so many real-world applications, ranging from facial recognition to language translators and assistants like Siri and Alexa, that we barely notice it. Along with these consumer applications, companies across sectors are increasingly harnessing AI's power in their operations. Embracing AI promises considerable benefits for businesses and economies through its contributions to productivity growth and innovation. At the same time, AI's impact on work is likely to be profound. Some occupations as well as demand for some skills will decline, while others grow and many change as people work alongside ever-evolving and increasingly capable machines.

At Arm Tech Con today, West Lake Village, Calif.-based startup Eta Compute showed off what it believes is the first commercial low-power AI chip capable of learning on its own using a type of machine learning called spiking neural networks. Most AI chips for use in low-power or battery-operated IoT devices have a neural network that has been trained by a more powerful computer to do a particular job. A neural network that can do what's called unsupervised learning can essentially train itself: Show it a pack of cards and it will figure out how to sort the threes from the fours from the fives. Eta Compute's third generation chip, called TENSAI, also does traditional deep learning using convolutional neural networks. Potential customers already have samples of the new chip, and the company expects to begin mass production in the first quarter of 2019.

Machine learning (ML) is touted as the most critical skill of current times. Artificial intelligence (AI), an application of ML, is becoming pervasive. From autonomous vehicles to self-tuned databases, AI and ML are found everywhere. Industry analysts often refer to AI-driven automation as the job killer. Almost every domain and industry vertical are getting impacted by AI and ML.

Deep neural networks (DNNs) have become an essential method for solving difficult tasks in computer vision, signal processing, and natural language processing (He et al., 2016; Choi et al., 2018; Han et al., 2017; Van Den Oord et al., 2016; Seo et al., 2016; Vaswani et al., 2017). As the capabilities of deep learning have expanded with more modular architectures and advanced optimization methods, the number of hyperparameters has increased in general. This increase of hyperparameter sizes makes it more difficult for a researcher to optimize a model, wasting a lot of human resources and potentially leading unfair comparisons. This reinforces the importance of efficient automated hyperparameter tuning methods and interfaces. To address this problem, several hyperparameter optimization (HyperOpt) methods have been proposed (Jaderberg et al., 2017; Falkner et al., 2018; Li et al., 2017). These methods have many advantages such as strong final performance, parallelism, early stopping which significantly improve performance in terms of computing resource efficiency and optimization time.

This work demonstrates a physical attack on a deep learning image classification system using projected light onto a physical scene. Prior work is dominated by techniques for creating adversarial examples which directly manipulate the digital input of the classifier. Such an attack is limited to scenarios where the adversary can directly update the inputs to the classifier. This could happen by intercepting and modifying the inputs to an online API such as Clarifai or Cloud Vision. Such limitations have led to a vein of research around physical attacks where objects are constructed to be inherently adversarial or adversarial modifications are added to cause misclassification. Our work differs from other physical attacks in that we can cause misclassification dynamically without altering physical objects in a permanent way. We construct an experimental setup which includes a light projection source, an object for classification, and a camera to capture the scene. Experiments are conducted against 2D and 3D objects from CIFAR-10. Initial tests show projected light patterns selected via differential evolution could degrade classification from 98% to 22% and 89% to 43% probability for 2D and 3D targets respectively. Subsequent experiments explore sensitivity to physical setup and compare two additional baseline conditions for all 10 CIFAR classes. Some physical targets are more susceptible to perturbation. Simple attacks show near equivalent success, and 6 of the 10 classes were disrupted by light.

Memorization of data in deep neural networks has become a subject of significant research interest. In this paper, we link memorization of images in deep convolutional autoencoders to downsampling through strided convolution. To analyze this mechanism in a simpler setting, we train linear convolutional autoencoders and show that linear combinations of training data are stored as eigenvectors in the linear operator corresponding to the network when downsampling is used. On the other hand, networks without downsampling do not memorize training data. We provide further evidence that the same effect happens in nonlinear networks. Moreover, downsampling in nonlinear networks causes the model to not only memorize linear combinations of images, but individual training images. Since convolutional autoencoder components are building blocks of deep convolutional networks, we envision that our findings will shed light on the important phenomenon of memorization in over-parameterized deep networks.

There is a perceived trade-off between machine learning code that is easy to write, and machine learning code that is scalable or fast to execute. In machine learning, imperative style libraries like Autograd and PyTorch are easy to write, but suffer from high interpretive overhead and are not easily deployable in production or mobile settings. Graph-based libraries like TensorFlow and Theano benefit from whole-program optimization and can be deployed broadly, but make expressing complex models more cumbersome. We describe how the use of staged programming in Python, via source code transformation, offers a midpoint between these two library design patterns, capturing the benefits of both. A key insight is to delay all type-dependent decisions until runtime, via dynamic dispatch. We instantiate these principles in AutoGraph, a software system that improves the programming experience of the TensorFlow library, and demonstrate usability improvements with no loss in performance compared to native TensorFlow graphs. We also show that our system is backend agnostic, and demonstrate targeting an alternate IR with characteristics not found in TensorFlow graphs.

This paper describes FBK's submission to the end-to-end English-German speech translation task at IWSLT 2018. Our system relies on a state-of-the-art model based on LSTMs and CNNs, where the CNNs are used to reduce the temporal dimension of the audio input, which is in general much higher than machine translation input. Our model was trained only on the audio-to-text parallel data released for the task, and fine-tuned on cleaned subsets of the original training corpus. The addition of weight normalization and label smoothing improved the baseline system by 1.0 BLEU point on our validation set. The final submission also featured checkpoint averaging within a training run and ensemble decoding of models trained during multiple runs. On test data, our best single model obtained a BLEU score of 9.7, while the ensemble obtained a BLEU score of 10.24.

In this paper, wireless video transmission to multiple users under total transmission power and minimum required video quality constraints is studied. In order to provide the desired performance levels to the end-users in real-time video transmissions while using the energy resources efficiently, we assume that power control is employed. Due to the presence of interference, determining the optimal power control is a non-convex problem but can be solved via monotonic optimization framework. However, monotonic optimization is an iterative algorithm and can often entail considerable computational complexity, making it not suitable for real-time applications. To address this, we propose a learning-based approach that treats the input and output of a resource allocation algorithm as an unknown nonlinear mapping and a deep neural network (DNN) is employed to learn this mapping. This learned mapping via DNN can provide the optimal power level quickly for given channel conditions.