In this paper we present a method for simultaneously segmenting brain tumors and an extensive set of organs-at-risk for radiation therapy planning of glioblastomas. The method combines a contrast-adaptive generative model for whole-brain segmentation with a new spatial regularization model of tumor shape using convolutional restricted Boltzmann machines. We demonstrate experimentally that the method is able to adapt to image acquisitions that differ substantially from any available training data, ensuring its applicability across treatment sites; that its tumor segmentation accuracy is comparable to that of the current state of the art; and that it captures most organs-at-risk sufficiently well for radiation therapy planning purposes. The proposed method may be a valuable step towards automating the delineation of brain tumors and organs-at-risk in glioblastoma patients undergoing radiation therapy.

Universal induction relies on some general search procedure that is doomed to be inefficient. One possibility to achieve both generality and efficiency is to specialize this procedure w.r.t. any given narrow task. However, complete specialization that implies direct mapping from the task parameters to solutions (discriminative models) without search is not always possible. In this paper, partial specialization of general search is considered in the form of genetic algorithms (GAs) with a specialized crossover operator. We perform a feasibility study of this idea implementing such an operator in the form of a deep feedforward neural network. GAs with trainable crossover operators are compared with the result of complete specialization, which is also represented as a deep neural network. Experimental results show that specialized GAs can be more efficient than both general GAs and discriminative models.

Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations, however, often becomes the main limitation. Due to privacy concerns and ethical considerations, most medical datasets are created, curated, and allow access only locally. Furthermore, current deep learning methods are often suboptimal in translating anatomical knowledge between different medical imaging modalities. Active learning can be used to select an informed set of image samples to request for manual annotation, in order to best utilize the limited annotation time of clinical experts for optimal outcomes, which we focus on in this work. Our contributions herein are two fold: (1) we enforce domain-representativeness of selected samples using a proposed penalization scheme to maximize information at the network abstraction layer, and (2) we propose a Borda-count based sample querying scheme for selecting samples for segmentation. Comparative experiments with baseline approaches show that the samples queried with our proposed method, where both above contributions are combined, result in significantly improved segmentation performance for this active learning task.

While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimization and Hyperband for efficient joint neural architecture and hyperparameter search.

Data-driven approaches to solving robotic tasks have gained a lot of traction in recent years. However, most existing policies are trained on large-scale datasets collected in curated lab settings. If we aim to deploy these models in unstructured visual environments like people's homes, they will be unable to cope with the mismatch in data distribution. In such light, we present the first systematic effort in collecting a large dataset for robotic grasping in homes. First, to scale and parallelize data collection, we built a low cost mobile manipulator assembled for under 3K USD. Second, data collected using low cost robots suffer from noisy labels due to imperfect execution and calibration errors. To handle this, we develop a framework which factors out the noise as a latent variable. Our model is trained on 28K grasps collected in several houses under an array of different environmental conditions. We evaluate our models by physically executing grasps on a collection of novel objects in multiple unseen homes. The models trained with our home dataset showed a marked improvement of 43.7% over a baseline model trained with data collected in lab. Our architecture which explicitly models the latent noise in the dataset also performed 10% better than one that did not factor out the noise. We hope this effort inspires the robotics community to look outside the lab and embrace learning based approaches to handle inaccurate cheap robots.

An important task for a recommender system to provide interpretable explanations for the user. This is important for the credibility of the system. Current interpretable recommender systems tend to focus on certain features known to be important to the user and offer their explanations in a structured form. It is well known that user generated reviews and feedback from reviewers have strong leverage over the users' decisions. On the other hand, recent text generation works have been shown to generate text of similar quality to human written text, and we aim to show that generated text can be successfully used to explain recommendations. In this paper, we propose a framework consisting of popular review-oriented generation models aiming to create personalised explanations for recommendations. The interpretations are generated at both character and word levels. We build a dataset containing reviewers' feedback from the Amazon books review dataset. Our cross-domain experiments are designed to bridge from natural language processing to the recommender system domain. Besides language model evaluation methods, we employ DeepCoNN, a novel review-oriented recommender system using a deep neural network, to evaluate the recommendation performance of generated reviews by root mean square error (RMSE). We demonstrate that the synthetic personalised reviews have better recommendation performance than human written reviews. To our knowledge, this presents the first machine-generated natural language explanations for rating prediction.

For starters, computers simply lacked the processing power to make things happen. Floppy disk-drive machines paled in sophistication compared with modern smartphones, and computer chips wouldn't hold a million components until 1989. Yet another obstacle dogged any dreams of AI from taking form. In 1984, the American Association of Artificial Intelligence held a fateful meeting where field pioneer Marvin Minsky, of all people, warned the business community that investor enthusiasm for artificial intelligence would eventually lead to disappointment. Sure enough, AI investment began to collapse.

But finding the sweet spot where human and machine effortlessly collaborate has proved elusive. Arjun Bansal, a founder of the artificial intelligence company Nervana, believes that seamless man-machine collaboration is coming. But when it arrives and how it will work will vary by industry. Nervana, founded in 2014 and acquired by Intel in 2016, built a full-stack software-as-a-service platform to allow businesses to develop their own proprietary customized deep learning software. Bansal was one of three founders of Nervana and now heads up the AI and deep learning team at Intel.

The researchers had data for 216,221 instances of hospitalisations with more than 100,000 unique patients. When predicted with DL, the experiment along the four outcomes: mortality, readmissions, long length of stay and discharge diagnosis show an accuracy of around 80 percent and above for both hospitals A and B, which is significantly higher than traditional prediction models. The DL model also improves with accuracy as the time interval period is expanded. The following figure shows a parameter called area under the receiver operating characteristic curve(AUROC) for the study.

In this article, we'll train a PyTorch model to perform super-resolution imaging, a technique for gracefully upscaling images. Super-resolution imaging (right) infers pixel values from a lower-resolution image (left). Machine learning projects typically begin by acquiring data, cleaning the data, and converting the data into model-native formats. Such manual data pipelines are tedious to create and difficult to reproduce over time, across collaborators, and across machines. Moreover, trained models are often stored haphazardly, without version control.