Studies suggest that within the hierarchical architecture, the topological higher level possibly represents a conscious category of the current sensory events with slower changing activities. They attempt to predict the activities on the lower level by relaying the predicted information. On the other hand, the incoming sensory information corrects such prediction of the events on the higher level by the novel or surprising signal. We propose a predictive hierarchical artificial neural network model that examines this hypothesis on neurorobotic platforms, based on the AFA-PredNet model. In this neural network model, there are different temporal scales of predictions exist on different levels of the hierarchical predictive coding, which are defined in the temporal parameters in the neurons. Also, both the fast and the slow-changing neural activities are modulated by the active motor activities. A neurorobotic experiment based on the architecture was also conducted based on the data collected from the VRep simulator.

Simultaneously utilizing several complementary solvers is a simple yet effective strategy for solving computationally hard problems. However, manually building such solver portfolios typically requires considerable domain knowledge and plenty of human effort. As an alternative, automatic construction of parallel portfolios (ACPP) aims at automatically building effective parallel portfolios based on a given problem instance set and a given rich design space. One promising way to solve the ACPP problem is to explicitly group the instances into different subsets and promote a component solver to handle each of them.This paper investigates solving ACPP from this perspective, and especially studies how to obtain a good instance grouping.The experimental results showed that the parallel portfolios constructed by the proposed method could achieve consistently superior performances to the ones constructed by the state-of-the-art ACPP methods,and could even rival sophisticated hand-designed parallel solvers.

In this paper, we propose the Cross-Domain Adversarial Auto-Encoder (CDAAE) to address the problem of cross-domain image inference, generation and transformation. We make the assumption that images from different domains share the same latent code space for content, while having separate latent code space for style. The proposed framework can map cross-domain data to a latent code vector consisting of a content part and a style part. The latent code vector is matched with a prior distribution so that we can generate meaningful samples from any part of the prior space. Consequently, given a sample of one domain, our framework can generate various samples of the other domain with the same content of the input. This makes the proposed framework different from the current work of cross-domain transformation. Besides, the proposed framework can be trained with both labeled and unlabeled data, which makes it also suitable for domain adaptation. Experimental results on data sets SVHN, MNIST and CASIA show the proposed framework achieved visually appealing performance for image generation task. Besides, we also demonstrate the proposed method achieved superior results for domain adaptation. Code of our experiments is available in https://github.com/luckycallor/CDAAE.

PYONGYANG – North Korea has recently started to introduce state-of-the-art technology for the training of future schoolteachers in a possible world first. At the newly remodeled Pyongyang Teacher Training College, the mostly female students study how to educate kindergartners and primary school children with the aid of virtual reality and 3D display technologies. A group of Kyodo News reporters was granted rare access to the college late last week. In one classroom is installed a large widescreen monitor on which are displayed animated avatars representing primary school pupils. Speaking to the virtual children through a microphone, they respond in a timely manner.

WASHINGTON – China is slightly ahead of South Korea and the United States in the race to develop fifth generation wireless networks, or 5G, a U.S. study showed Monday. The study released by the CTIA, a U.S.-based industry association of wireless carriers, suggested that the United States is lagging in the effort to deploy the superfast wireless systems that will be needed for self-driving cars, telemedicine and other technologies. The report prepared by the research firm Analysys Mason found that all major Chinese providers have committed to specific launch dates and the government has committed to allocate spectrum for the carriers. The 10-nation study said the U.S. is in the "first tier" of countries in preparing deployment of 5G, along with China, South Korea and Japan. In the second tier are key European markets, including France, Germany and Britain, with Singapore, Russia and Canada in the third tier.

If you're like the unbreakable Kimmy Schmidt and got stuck in a bomb shelter in 2017, it may be both a blessing and a curse that you missed the machine learning for marketing media frenzy. Machine learning showed up everywhere, rivaling electricity's systemic emergence a century ago, allegedly injecting sage-like wisdom into everything from sales forecasting tools to email subject lines generators. But buildup and hype aside, real progress was made in using machine learning for marketing purposes, infiltrating impactful areas as unprecedented investments poured in. More resources supporting great minds pushed forward innovation in areas like image recognition, voice technologies, and natural language generation (NLG). And savvy brands that mindfully wired these into marketing applications boosted performance, in some cases realizing 400 percent ROI.

Intel, which wowed folks with its syncronized drone show at the Olympics, is at it again, with a drone show at the Coachella music festival near Palm Springs Sunday. We sit down with an Intel exec who explains how it works, and why Intel is pushing the idea of dancing drones. LOS ANGELES -- Intel, once best known as the company that powered PCs and Macs with its silicon chips, is now perhaps better known to the public for its awesome drone light shows. The company doesn't make consumer drones nor does it have plans to take on DJI or Yuneec, but it's become a frequent visitor to high profile events like the Super Bowl and Olympics with synchronized aerial drone shows. The Olympics alone had 1,218 drones in the air at one time, forming five Olympic rings and other intricate figures.

AI and robotics are going to shape our future. Next there are 10 issues that professionals and researchers need to address in order to desing intelligent systems that help humanity. The flow of misinformation together with our natural inability of perceiving reality based on evidence (a phenomenon called confirmation bias) is a threat to having an informed democracy. Russian hackers influencing the US elections, Brexit campaign and Catalonia crisis are examples of how social media can massively spread misinformation and fake news. It is an open question how institutions are going to address this threat. The scientific revolution in the 18th century and the industrial revolution in the 19th marked a complete change in society.

AI will augment people's capabilities but won't take all jobs. However, there will be socioeconomic upheaval, warns PwC's authority on AI, Anand Rao. Anand Rao is PwC global leader for artificial intelligence (AI) and is the consulting giant's innovation lead for the US analytics practice. Rao has 24 years of industry and consulting experience, helping senior executives to structure, solve and manage critical issues facing their organisations. He has worked extensively on business, technology and analytics issues across a wide range of industry sectors including financial services, healthcare, telecommunications, aerospace and defence, across US, Europe, Asia and Australia.

The House of Lords report on the implications of artificial intelligence is a thoughtful document which grasps one rather important point: this is not only something that computers do. Machine learning is the more precise term for the technology that allows computers to recognise patterns in enormous datasets and act on them. But even machine learning doesn't happen only inside computer networks, because these machines are constantly tended and guided by humans. You can't say that Google's intelligence resides either in its machines or in its people: it depends on both and emerges from their interplay. Complex software is never written to a state of perfection and then left to run for ever.