In January 2016, the Obama administration set aside four billion dollars to fast-forward the development and implementation of self-driving vehicles through real-world pilot projects. Without a doubt, self-driving vehicles will be safer than any cars driven by humans. In fact, it's estimated that autonomous vehicles will reduce traffic accidents by 94 percent. So, whether you're for or against self-driving cars, there's no turning back -- the future is here. But before we get too ahead of ourselves, there are still some kinks we need to work out.

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node's network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-of-the-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks.

Community-based Question Answering (CQA) sites play an important role in addressing health information needs. However, a significant number of posted questions remain unanswered. Automatically answering the posted questions can provide a useful source of information for online health communities. In this study, we developed an algorithm to automatically answer health-related questions based on past questions and answers (QA). We also aimed to understand information embedded within online health content that are good features in identifying valid answers. Our proposed algorithm uses information retrieval techniques to identify candidate answers from resolved QA. In order to rank these candidates, we implemented a semi-supervised leaning algorithm that extracts the best answer to a question. We assessed this approach on a curated corpus from Yahoo! Answers and compared against a rule-based string similarity baseline. On our dataset, the semi-supervised learning algorithm has an accuracy of 86.2%. UMLS-based (health-related) features used in the model enhance the algorithm's performance by proximately 8 %. A reasonably high rate of accuracy is obtained given that the data is considerably noisy. Important features distinguishing a valid answer from an invalid answer include text length, number of stop words contained in a test question, a distance between the test question and other questions in the corpus as well as a number of overlapping health-related terms between questions. Overall, our automated QA system based on historical QA pairs is shown to be effective according to the data set in this case study. It is developed for general use in the health care domain which can also be applied to other CQA sites.

A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods on several datasets, including ShapeNet [2], and establish the first benchmarks in the literature. We also show how these models and their inference networks can be trained end-to-end from 2D images. This demonstrates for the first time the feasibility of learning to infer 3D representations of the world in a purely unsupervised manner.

The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it is possible to simplify the NN during training process to achieve a reasonable performance within an acceptable computational time. We presented a novel approach of optimising a deep neural network through regularisation of network architecture. We proposed regularisers which support a simple mechanism of dropping neurons during a network training process. The method supports the construction of a simpler deep neural networks with compatible performance with its simplified version. As a proof of concept, we evaluate the proposed method with examples including sparse linear regression, deep autoencoder and convolutional neural network. The valuations demonstrate excellent performance. The code for this work can be found in http://www.github.com/panweihit/

We propose an adaptive smoothing algorithm based on Nesterov's smoothing technique in \cite{Nesterov2005c} for solving "fully" nonsmooth composite convex optimization problems. Our method combines both Nesterov's accelerated proximal gradient scheme and a new homotopy strategy for smoothness parameter. By an appropriate choice of smoothing functions, we develop a new algorithm that has the $\mathcal{O}\left(\frac{1}{\varepsilon}\right)$-worst-case iteration-complexity while preserves the same complexity-per-iteration as in Nesterov's method and allows one to automatically update the smoothness parameter at each iteration. Then, we customize our algorithm to solve four special cases that cover various applications. We also specify our algorithm to solve constrained convex optimization problems and show its convergence guarantee on a primal sequence of iterates. We demonstrate our algorithm through three numerical examples and compare it with other related algorithms.

As the automation of physical and knowledge work advances, many jobs will be redefined rather than eliminated--at least in the short term. The potential of artificial intelligence and advanced robotics to perform tasks once reserved for humans is no longer reserved for spectacular demonstrations by the likes of IBM's Watson, Rethink Robotics' Baxter, DeepMind, or Google's driverless car. Just head to an airport: automated check-in kiosks now dominate many airlines' ticketing areas. Pilots actively steer aircraft for just three to seven minutes of many flights, with autopilot guiding the rest of the journey. Passport-control processes at some airports can place more emphasis on scanning document bar codes than on observing incoming passengers.

In the not-so-distant future, children will be amazed by stories that we allowed relative strangers to steer one tonne machines, relying on human skill and instinct over the capabilities of computers. The field of artificial intelligence has a transformative capability over many things that govern our daily lives. Consider self-driving cars: about 33,000 people are killed in automobile accidents in the US every year and most fatalities can be traced back to humans. Companies across technology and automobile industries are pouring millions of dollars into using AI to drive new breakthroughs in this field. Already, cars by Tesla have limited self-drive capabilities and we will soon see this rapidly increasing.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

Companies like Google, AWS and Microsoft have introduced their own machine learning platform in cloud. In this blog, we are going to share my experience while getting started with machine learning platform. Very first question that I ask myself was "Why this provider?"