Relation extraction, which learns semantic relations of concept pairs from text, is an approach for mining commonsense knowledge. This paper investigates an approach for relation extraction, which helps expand a commonsense knowledge base with little labor work. We proposed a framework that learns new pairs from Chinese corpora by adopting concept pairs in Chinese commonsense knowledge base as seeds. Multiple instance learning is utilized as the learning algorithm for predicting relation for unseen pairs. The performance of our system could be improved by learning multiple iterations. The results in each iteration are manually evaluated and processed to next iteration as seeds. Our experiments extracted new pairs for relations “AtLocation”, “CapableOf”, and “HasProperty”. This study showed that new pairs could be extracted from text without huge humans work.

As another example, to achieve high accuracy in recommender systems [45], [60], we need to fully understand the content of items (e.g., documents and movies), analyze the profile and preference of users, and evaluate the similarity among users. Deep learning is good at the first subtask while PGM excels at the other two. Besides the fact that better understanding of item content would help with the analysis of user profiles, the estimated similarity among users could provide valuable information for understanding item content in return. In order to fully utilize this bidirectional effect to boost recommendation accuracy, we might wish to unify deep learning and PGM in one single principled probabilistic framework, as done in [60]. Besides recommender systems, the need for Bayesian deep learning may also arise when we are dealing with control of nonlinear dynamical systems with raw images as input. Consider controlling a complex dynamical system according to the live video stream received from a camera. This problem can be transformed into iteratively performing two tasks, perception from raw images and control based on dynamic models. The perception task can be taken care of using multiple layers of simple nonlinear transformation (deep learning) while the control task usually needs more sophisticated models like hidden Markov models and Kalman filters [21], [38]. The feedback loop is then completed by the fact that actions chosen by the control model can affect the received video stream in return.

Emotional intelligence is a cornerstone of human interactions--an essential part of what it means to be human. But now, artificial intelligences are being developed to better read and process human emotions, which is already changing the way we interact with robots. In the early 1990s, psychologists Salovey and Mayer were the first to recognize emotional intelligence as a set of knowledge and skills distinct from other forms of intelligence, defining it as "the ability to monitor one's own and other's feelings and emotions, to discriminate among them, and to use this information to guide one's thinking and actions." Emotional intelligence is something that seems wonderfully and innately human. But it turns out the tenets of emotional intelligence--which we start picking up in infancy and which seem so closely linked to human nature itself--can be quantified and reduced to logical procedures and algorithms.

The task of algorithm selection involves choosing an algorithm from a set of algorithms on a per-instance basis in order to exploit the varying performance of algorithms over a set of instances. The algorithm selection problem is attracting increasing attention from researchers and practitioners in AI. Years of fruitful applications in a number of domains have resulted in a large amount of data, but the community lacks a standard format or repository for this data. This situation makes it difficult to share and compare different approaches effectively, as is done in other, more established fields. It also unnecessarily hinders new researchers who want to work in this area. To address this problem, we introduce a standardized format for representing algorithm selection scenarios and a repository that contains a growing number of data sets from the literature. Our format has been designed to be able to express a wide variety of different scenarios. Demonstrating the breadth and power of our platform, we describe a set of example experiments that build and evaluate algorithm selection models through a common interface. The results display the potential of algorithm selection to achieve significant performance improvements across a broad range of problems and algorithms.

Machine learning is an artificial intelligence branch that has been well applied and recognized as an effective tool to handle a wide range of real situations. In the last few years, we have witnessed the explosion of Big Data, which has enables researchers to store data for analysis in an unprecedented way. This explosion in data available for analysis is as evident in healthcare as anywhere else. In particular, this special issue is focused on the areas of bioinformatics and biomedical engineering. These are two of the fastest developing research fields in the last few decades, since the biological data used to provide information is rapidly generated, and it is mandatory to be able to extract information and knowledge from them, as technological innovation in these fields is to be probably one of the most important developments in the next coming years.

Next time you ask Google for directions or run an image search, thank Le Viet Quoc. The 34-year-old Vietnamese engineer is part of the team behind Google Brain, an artificial intelligence (AI) research project whose technology is responsible for such features, reports VnExpress. Part of Google's not-so-secret research outfit X, which pioneers cutting-edge technology like self-driving cars and delivery drones, Quoc works in a field known as "deep learning" which uses the human brain as a model to create "neural networks" for computers. Though deep learning's development has been slow, engineers like Quoc are making progress: in 2012, Google Brain made headlines when its network of 16,000 computer processors successfully learned how to search for cat videos on YouTube, despite being given no information prior to the test on how to identify such animals. The Stanford grad, who holds a doctorate in computer science and was named one of MIT's Innovators Under 35, is still working toward the creation of better, more intelligent machines.

This article discusses the quadratization of Markov Logic Networks, which enables efficient approximate MAP computation by means of maximum flows. The procedure relies on a pseudo-Boolean representation of the model, and allows handling models of any order. The employed pseudo-Boolean representation can be used to identify problems that are guaranteed to be solvable in low polynomial-time. Results on common benchmark problems show that the proposed approach finds optimal assignments for most variables in excellent computational time and approximate solutions that match the quality of ILP-based solvers.

Regularized least-squares approaches have been successfully applied to linear system identification. Recent approaches use quadratic penalty terms on the unknown impulse response defined by stable spline kernels, which control model space complexity by leveraging regularity and bounded-input bounded-output stability. This paper extends linear system identification to a wide class of nonsmooth stable spline estimators, where regularization functionals and data misfits can be selected from a rich set of piecewise linear quadratic penalties. This class encompasses the 1-norm, huber, and vapnik, in addition to the least-squares penalty, and the approach allows linear inequality constraints on the unknown impulse response. We develop a customized interior point solver for the entire class of proposed formulations. By representing penalties through their conjugates, we allow a simple interface that enables the user to specify any piecewise linear quadratic penalty for misfit and regularizer, together with inequality constraints on the response. The solver is locally quadratically convergent, with O(n2(m+n)) arithmetic operations per iteration, for n impulse response coefficients and m output measurements. In the system identification context, where n << m, IPsolve is competitive with available alternatives, illustrated by a comparison with TFOCS and libSVM. The modeling framework is illustrated with a range of numerical experiments, featuring robust formulations for contaminated data, relaxation systems, and nonnegativity and unimodality constraints on the impulse response. Incorporating constraints yields significant improvements in system identification. The solver used to obtain the results is distributed via an open source code repository.

Global technology leaders and senior executives from around the world spoke on a range of topics, including Digital India, Smart Cities, Make in India, Skill India and cutting-edge technologies such as artificial intelligence, machine learning, 3D printing, drones, robotics, robotic surgeries and genomics, at the two-day EmTech India 2016 event, held in New Delhi on 18 and 19 March. The event was organized by Mint and MIT Technology Review, published by the Massachusetts Institute of Technology (MIT). The speakers included Jack Hidary, senior adviser at Google X Labs; Bhaskar Pramanik, chairman of Microsoft India; and Sharad Sharma, co-founder of think tank iSPIRT. The full list can be accessed at emtech.livemint.com/speakers. Here are edited excerpts from their speeches. A moonshot is an initiative that accompanies a goal that was previously thought to be near impossible. Moonshot philosophy sounds like it is quite radical and risky, but actually it is low-risk. That is because it attracts the best human capital and finance. Moonshot approaches do a few things. First, they attract the best human capital, which is a key driver of growth. They attract the best financial capital as well; capital from big and long-term thinkers. One describes India as a moonshot nation. India itself is going through a radical transformation--the likes of what we have never seen. This is very different to what is happening in China or any other country in the world. It is a combination of smartphones, digital payments, broadband and power of energy storage coming together. Smartphones ease the access to the Internet and open up users to mobile apps and that really changes the name of the game.

This post is the first in a series I'll be writing for Parallel Forall that aims to provide an intuitive and gentle introduction to deep learning. It covers the most important deep learning concepts and aims to provide an understanding of each concept rather than its mathematical and theoretical details. While the mathematical terminology is sometimes necessary and can further understanding, these posts use analogies and images whenever possible to provide easily digestible bits comprising an intuitive overview of the field of deep learning. I wrote this series in a glossary style so it can also be used as a reference for deep learning concepts. Part 1 focuses on introducing the main concepts of deep learning. Part 2 provides historical background and delves into the training procedures, algorithms and practical tricks that are used in training for deep learning. Part 3 covers sequence learning, including recurrent neural networks, LSTMs, and encoder-decoder systems for neural machine translation.