In order to submit a claim to insurance companies, a doctor needs to code a patient encounter with both the diagnosis (ICDs) and procedures performed (CPTs) in an Electronic Health Record (EHR). Identifying and applying relevant procedures code is a cumbersome and time-consuming task as a doctor has to choose from around 13,000 procedure codes with no predefined one-to-one mapping. In this paper, we propose a state-of-the-art deep learning method for automatic and intelligent coding of procedures (CPTs) from the diagnosis codes (ICDs) entered by the doctor. Precisely, we cast the learning problem as a multi-label classification problem and use distributed representation to learn the input mapping of high-dimensional sparse ICDs codes. Our final model trained on 2.3 million claims is able to outperform existing rule-based probabilistic and association-rule mining based methods and has a recall of 90@3.

Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve accuracy and result in better products. As DL application domains grow, we would like a deeper understanding of the relationships between training set size, computational scale, and model accuracy improvements to advance the state-of-the-art. This paper presents a large scale empirical characterization of generalization error and model size growth as training sets grow. We introduce a methodology for this measurement and test four machine learning domains: machine translation, language modeling, image processing, and speech recognition. Our empirical results show power-law generalization error scaling across a breadth of factors, resulting in power-law exponents---the "steepness" of the learning curve---yet to be explained by theoretical work. Further, model improvements only shift the error but do not appear to affect the power-law exponent. We also show that model size scales sublinearly with data size. These scaling relationships have significant implications on deep learning research, practice, and systems. They can assist model debugging, setting accuracy targets, and decisions about data set growth. They can also guide computing system design and underscore the importance of continued computational scaling.

This paper presents a novel framework for generating texture mosaics with convolutional neural networks. Our method is called GANosaic and performs optimization in the latent noise space of a generative texture model, which allows the transformation of a content image into a mosaic exhibiting the visual properties of the underlying texture manifold. To represent that manifold, we use a state-of-the-art generative adversarial method for texture synthesis [1], which can learn expressive texture representations from data and produce mosaic images with very high resolution. This fully convolutional model generates smooth (without any visible borders) mosaic images which morph and blend different textures locally. In addition, we develop a new type of differentiable statistical regularization appropriate for optimization over the prior noise space of the PSGAN model.

End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used log-scaled mel-spectrogram transformation. Secondly, we demonstrate that upon initializing the first layers of an end-to-end CNN classifier with the learned transformation, convergence and performance on the ESC-50 environmental sound classification dataset are similar to a CNN-based model trained on the highly pre-processed log-scaled mel-spectrogram features.

Though suicide is a major public health problem in the US, machine learning methods are not commonly used to predict an individual's risk of attempting/committing suicide. In the present work, starting with an anonymized collection of electronic health records for 522,056 unique, California-resident adolescents, we develop neural network models to predict suicide attempts. We frame the problem as a binary classification problem in which we use a patient's data from 2006-2009 to predict either the presence (1) or absence (0) of a suicide attempt in 2010. After addressing issues such as severely imbalanced classes and the variable length of a patient's history, we build neural networks with depths varying from two to eight hidden layers. For test set observations where we have at least five ED/hospital visits' worth of data on a patient, our depth-4 model achieves a sensitivity of 0.703, specificity of 0.980, and AUC of 0.958.

Developing neural network image classification models often requires significant architecture engineering. In this paper, we attempt to automate this engineering process by learning the model architectures directly on the dataset of interest. As this approach is expensive when the dataset is large, we propose to search for an architectural building block on a small dataset and then transfer the block to a larger dataset. Our key contribution is the design of a new search space which enables transferability. In our experiments, we search for the best convolutional layer (or "cell") on the CIFAR-10 dataset and then apply this cell to the ImageNet dataset by stacking together more copies of this cell, each with their own parameters. Although the cell is not searched for directly on ImageNet, an architecture constructed from the best cell achieves, among the published works, state-of-the-art accuracy of 82.7% top-1 and 96.2% top-5 on ImageNet. Our model is 1.2% better in top-1 accuracy than the best human-invented architectures while having 9 billion fewer FLOPS -- a reduction of 28% in computational demand from the previous state-of-the-art model. When evaluated at different levels of computational cost, accuracies of our models exceed those of the state-of-the-art human-designed models. For instance, a smaller network constructed from the best cell also achieves 74% top-1 accuracy, which is 3.1% better than equivalently-sized, state-of-the-art models for mobile platforms. On CIFAR-10, an architecture constructed from the best cell achieves 2.4% error rate, which is also state-of-the-art. Finally, the image features learned from image classification can also be transferred to other computer vision problems. On the task of object detection, the learned features used with the Faster-RCNN framework surpass state-of-the-art by 4.0% achieving 43.1% mAP on the COCO dataset.

Motivated by the problem of computer-aided detection (CAD) of pulmonary nodules, we introduce methods to propagate and fuse uncertainty information in a multi-stage Bayesian convolutional neural network (CNN) architecture. The question we seek to answer is "can we take advantage of the model uncertainty provided by one deep learning model to improve the performance of the subsequent deep learning models and ultimately of the overall performance in a multi-stage Bayesian deep learning architecture?". Our experiments show that propagating uncertainty through the pipeline enables us to improve the overall performance in terms of both final prediction accuracy and model confidence.

I'm standing in what is soon to be the center of the world, or is perhaps just a very large room on the seventh floor of a gleaming tower in downtown Toronto. Showing me around is Jordan Jacobs, who cofounded this place: the nascent Vector Institute, which opens its doors this fall and which is aiming to become the global epicenter of artificial intelligence. We're in Toronto because Geoffrey Hinton is in Toronto, and Geoffrey Hinton is the father of "deep learning," the technique behind the current excitement about AI. "In 30 years we're going to look back and say Geoff is Einstein--of AI, deep learning, the thing that we're calling AI," Jacobs says. Of the researchers at the top of the field of deep learning, Hinton has more citations than the next three combined. His students and postdocs have gone on to run the AI labs at Apple, Facebook, and OpenAI; Hinton himself is a lead scientist on the Google Brain AI team. The Vector Institute, this monument to the ascent of Hinton's ideas, is a research center where companies from around the U.S. and Canada--like Google, and Uber, and Nvidia--will sponsor efforts to commercialize AI technologies. Money has poured in faster than Jacobs could ask for it; two of his cofounders surveyed companies in the Toronto area, and the demand for AI experts ended up being 10 times what Canada produces every year. Vector is in a sense ground zero for the now-worldwide attempt to mobilize around deep learning: to cash in on the technique, to teach it, to refine and apply it. Data centers are being built, towers are being filled with startups, a whole generation of students is going into the field.

Hyderabad, 15th November 2017: Times Professional Learning recently conducted a Deep Learning Workshop at Hyderabad, in association with its technology partner NVIDIA. The one day workshop got a good response from the technology enthusiasts of Hyderabad. The instructor-led NVIDIA Deep Learning Institute (DLI) Master Class on deep learning helped students and professionals understand various aspects of Machine Learning and Artificial Intelligence (AI). NVIDIA Deep Learning Institute (NVDLI) focuses on an instructor-led training for developers, data scientists and researchers. It was the first among a series of workshops to be conducted all across India at major cities such as Mumbai, New Delhi, Chennai, Pune and Bengaluru.

It may look like a mild-mannered home security camera, but Amazon's AWS DeepLens is anything but. Announced today at the AWS re:Invent 2017 conference, the $249 (£185/AU$330 converted) DeepLens video camera is designed to help train developers in deep learning programming techniques. April 14, 2018, is the projected date of availability on Amazon.com, Deep learning has become a catch-all term for the AI smarts that dominate today's smart home. It's what fuels Amazon's Alexa-enabled speakers, what makes them able to differentiate among various voices, and what makes facial recognition cameras able to distinguish you from your neighbor. And they're only getting smarter -- at least, that's Amazon's hope.