DNNs are ubiquitous datacenter workloads, requiring orders of magnitude more computing power from servers than traditional workloads. As such, datacenter operators are forced to adopt domain-specific accelerators that employ half-precision floating-point (FP) numeric representations to improve arithmetic density. Unfortunately, even these representations are not dense enough, and are, therefore, sub-optimal for DNNs. We propose a hybrid approach that employs dense block floating-point (BFP) arithmetic on dot product computations and FP arithmetic elsewhere. While using BFP improves the performance of dot product operations, that compose most of DNN computations, allowing values to freely float between dot product operations leads to a better choice of tensor exponents when converting values to back BFP. We show that models trained with hybrid BFP-FP arithmetic either match or outperform their FP32 counterparts, leading to more compact models and denser arithmetic in computing platforms.

Many modern applications deal with multi-label data, such as functional categorizations of genes, image labeling and text categorization. Classification of such data with a large number of labels and latent dependencies among them is a challenging task, and it becomes even more challenging when the data is received online and in chunks. Many of the current multi-label classification methods require a lot of time and memory, which make them infeasible for practical real-world applications. In this paper, we propose a fast linear label space dimension reduction method that transforms the labels into a reduced encoded space and trains models on the obtained pseudo labels. Additionally, it provides an analytical method to update the decoding matrix which maps the labels into the original space and is used during the test phase. Experimental results show the effectiveness of this approach in terms of running times and the prediction performance over different measures. Keywords: data stream classification, multi-label data, label compression 1. Introduction Standard classification is the task of assigning the correct class to previously unknown test instances based on training instances. Training data consist of a set of features and an associated target class or class label. Many modern data mining applications, however, need to deal with more than one label per instance.

Word embeddings have emerged as a popular approach to unsupervised learning of word relationships in machine learning and natural language processing. In this article, we benchmark two of the most popular algorithms, GloVe and word2vec, to assess their suitability for capturing medical relationships in large sources of biomedical data. Leaning on recent theoretical insights, we provide a unified view of these algorithms and demonstrate how different sources of data can be combined to construct the largest ever set of embeddings for 108,477 medical concepts using an insurance claims database of 60 million members, 20 million clinical notes, and 1.7 million full text biomedical journal articles. We evaluate our approach, called cui2vec, on a set of clinically relevant benchmarks and in many instances demonstrate state of the art performance relative to previous results. Finally, we provide a downloadable set of pre-trained embeddings for other researchers to use, as well as an online tool for interactive exploration of the cui2vec embeddings.

Andrew Ng's five courser aims to give newbies and practitioners a crash course on all things deep learning – from fully connected neural networks to convolutional nets to sequence models. I've taken all five courses, and completed four. For some more online course recommendations, check out the best online courses to get started with data science. The first course in the specialization focuses on the building blocks of deep learning. It goes over logistic regression interpreted as a one-layer network, shallow networks, and finally deep networks as stacked shallow networks. Well, if you've taken Andrew Ng's precursor course Machine Learning, then the first course in Deep Learning is basically just an elaboration of the neural network part.

Deep Learning, one of the subfields of Machine Learning and Statistical Learning has been advancing in impressive levels in the past years. Cloud computing, robust open source tools and vast amounts of available data have been some of the levers for these impressive breakthroughs. The criteria used to select the 20 top papers is by using citation counts from academic.microsoft.com. It is important to mention that these metrics are changing rapidly so the citations valued must be considered as the numbers when this article was published. In this list of papers more than 75% refer to deep learning and neural networks, specifically Convolutional Neural Networks (CNN).

From time to time, the Singularity Hub editorial team unearths a gem from the archives and wants to share it all over again. It's usually a piece that was popular back then and we think is still relevant now. This is one of those articles. It was originally published June 19, 2016. We hope you enjoy it!

The real progress in machine learning is that, beyond quantitative and categorical data, we can now build models for images and text. These models can recognize objects and process language at the level of an average six-year-old human (yes, "human level"). Major tech companies -- many of which are in advertising too -- already leverage these models: think Facebook friend-tagging and Amazon answers. We believe there are opportunities to use these models for native advertising. More specifically, we can build image and text models to analyze the content of native ads and the content of publishers at scale, in order to find the best "fit." In addition, we want to build these models in an open and interpretable way, rather than simply using a catchy name that includes "AI." In doing so, Qchain hopes to help both advertisers and publishers meet their goals more efficiently with the right audiences -- forging a path for more authentic marketing.

Lightbeam is positioned to expand your ability to deliver care in an efficient way using artificial intelligence (AI) insights. In my most recent blog post, I shared what AI is and the use cases for it within the population health management realm. Many companies are beginning to integrate machine learning and deep learning into their offerings and I want to better explain the technology, so you can differentiate product offerings. We live in a data-driven analytic world where providers are trying to figure out the most efficient ways to solve problems and improve care. Artificial intelligence tries to solve problems using advanced understanding, learning, and reasoning.

Take a look at the three ramen bowls below. Can you believe that a machine learning (ML) model can identify the exact shop each bowl is made at, out of 41 ramen shops, with 95% accuracy? Data scientist Kenji Doi built an AI-enabled ramen expert classifier that can discern the minute details that make one shop's bowl of ramen different from the next one's. Ramen Jiro is one of the most popular chain restaurant franchises for ramen fans in Japan, because of its generous portions of toppings, noodles, and soup served at low prices. They have 41 branches around Tokyo, and they serve the same basic menu at each shop.

Call scoring is a crucial part of a call center quality assurance. It enables organizations to fine-tune the workflow so that call center agents can do their job faster and more efficiently, and also avoid meaningless routine work. With call center productivity in mind, our R&D team has been working on automated call scoring for the last couple of months. They've come up with an algorithm that processes all incoming calls and divides them into suspicious and neutral. All calls that are defined as suspicious go directly to a quality assurance team.