Many real-world relations can be represented by signed networks with positive and negative links, as a result of which signed network analysis has attracted increasing attention from multiple disciplines. With the increasing prevalence of social media networks, signed network analysis has evolved from developing and measuring theories to mining tasks. In this article, we present a review of mining signed networks in the context of social media and discuss some promising research directions and new frontiers. We begin by giving basic concepts and unique properties and principles of signed networks. Then we classify and review tasks of signed network mining with representative algorithms. We also delineate some tasks that have not been extensively studied with formal definitions and also propose research directions to expand the field of signed network mining.

Google's DeepMind has conquered some big artificial intelligence challenges in its day, such as defeating Go's world champion and navigating mazes through virtual sight. However, one of its accomplishments is decidedly unusual: it learned how to play soccer (aka football) with a digital ant. It looks cute, but it's really a profound test of DeepMind's asynchronous, reinforcement-based learning process. The AI has to not only learn how to move the ant without any prior understanding of its mechanics, but to kick the ball into a goal. Imagine if you had to learn how to run while playing your first-ever match -- that's how complex this is.

We get asked a lot of questions about how to start building with Watson, so we decided to compile our top 4 Frequently Asked Questions. You can use this as a guide to learn more about the technology, receive inspiration from use cases, get valuable resources, and ultimately begin building with the technology. Cognitive technology's strength lies in its ability to draw insights from unstructured data sets. Structured data is found in a spreadsheet, whereas unstructured data is text such as tweets, medical journals, etc. Today 80% of data is unstructured, so tools such as cognitive computing are becoming more important in helping humans understand what's inside that data.

Large-scale brain-like machines with human-like abilities to solve problems could become a reality, now that researchers have invented microscopic gadgets that mimic the connections between neurons in the human brain better than any previous devices. The new research could lead to better robots, self-driving cars, data mining, medical diagnosis, stock-trading analysis and "other smart human-interactive systems and machines in the future," said Tae-Woo Lee, a materials scientistat the Pohang University of Science and Technology in Korea and senior author of the study. The human brain's enormous computing power stems from its connections. Previous research suggested that the brain has approximately 100 billion neurons and roughly 1 quadrillion (1 million billion) connections wiring these cells together. At each of these connections, or synapses, a neuron typically fires about 10 times per second.

"I think being radical is the only way of doing things, because slow iteration doesn't really work." Claned Co-founder Vesa Perala believes that instead of attempting to retrofit technology to out-dated educational systems, EdTech start-ups should be helping to write a new rulebook. "Our pitch pretty much begins with education reform. The starting point is that the Finnish schooling system might be perceived as being the best in the world, but we're still overhauling it," he says. For the past 3 years, Claned has been in what he describes as semi-stealth mode, focusing on developing a robust artificial intelligence system that uses machine-learning algorithms to map out what factors most impact individual learning.

Kaggle competitions are a fantastic way to learn data science and build your portfolio. I personally used Kaggle to learn many data science concepts. I started out with Kaggle a few months after learning programming, and later won several competitions. Doing well in a Kaggle competition requires more than just knowing machine learning algorithms. It requires the right mindset, the willingness to learn, and a lot of data exploration. Many of these aspects aren't typically emphasized in tutorials on getting started with Kaggle, though. In this post, I'll cover how to get started with the Kaggle Expedia hotel recommendations competition, including establishing the right mindset, setting up testing infrastructure, exploring the data, creating features, and making predictions.

It was a dark, overcast day, with clouds hovering low. The room was kept at the most appropriate temperatures and humidity, as usual. Yoko sat on a couch in an untidy manner, killing time with a silly game. But she would not talk to me. So begins a short story titled "A day when a computer writes fiction."

Leading global IT services company HCL Technologies has been named winner of the'Best Innovation in Natural Language Processing (NLP)' award at the AIconics Awards during the "AI Summit" in London recently. AIconics are the world's only independently judged awards celebrating the drive, innovation and hard work in the international Artificial Intelligence (AI) community. "This award gives testimony to the innovation and pragmatic implementation of'Natural Language Processing' in the 21st century enterprise," Kalyan Kumar, executive vice president at HCL Technologies, said in a statement. HCL was also named as a finalist in the "Best Intelligent Assistant" category which showcases companies making ground-breaking advancements in virtual assistants and advanced voice/text recognition capabilities. The driving force behind HCL's success at the AIconics Awards is "HCL DryICE" -- the company's innovative autonomics and orchestration framework.

Both Amazon and Google are advancing their efforts in machine learning, a type of artificial intelligence that lets computers learn without being explicitly programmed. It's often associated with cloud computing, because it requires the considerable computing power the cloud makes easily available. Amazon's efforts will get a boost when Alexander Smola, a professor in the machine-learning department at Carnegie Mellon University, leaves that position July 1 to head Amazon's cloud machine-learning platform. Smola revealed his plans in this blog post. "This is a terrific task, and it was an offer that I could not turn down," Smola wrote.

ABSTRACT Deep neural networks (DNNs) have been successfully applied to a wide variety of acoustic modeling tasks in recent years. These include the applications of DNNs either in a discriminative feature extraction or in a hybrid acoustic modeling scenario. Despite the rapid progress in this area, a number of challenges remain in training DNNs. This paper presents an effective way of training DNNs using a manifold learning based regularization framework. In this framework, the parameters of the network are optimized to preserve underlying manifold based relationships between speech feature vectors while minimizing a measure of loss between network outputs and targets. This is achieved by incorporating manifold based locality constraints in the objective criterion of DNNs. Empirical evidence is provided to demonstrate that training a network with manifold constraints preserves structural compactness in the hidden layers of the network. Manifold regularization is applied to train bottleneck DNNs for feature extraction in hidden Markov model (HMM) based speech recognition. The experiments in this work are conducted on the Aurora-2 spoken digits and the Aurora-4 read news large vocabulary continuous speech recognition tasks. The performance is measured in terms of word error rate (WER) on these tasks. It is shown that the manifold regularized DNNs result in up to 37% reduction in WER relative to standard DNNs. Index Terms-- manifold learning, deep neural networks, manifold regularization, manifold regularized deep neural networks, speech recognition 1. INTRODUCTION Recently there has been a resurgence of research in the area of deep neural networks (DNNs) for acoustic modeling in automatic speech recognition (ASR) [1-6]. Much of this research has been concentrated on techniques for regularization of the algorithms used for DNN parameter estimation [7-9]. At the same time, there has also been a great deal of research on graph based techniques that facilitate the preservation of local neighborhood relationships among feature vectors for parameter estimation in a number of application areas [10-13]. Algorithms that preserve these local relationships are often referred to as having the effect of applying manifold based constraints.