The next wave of on-device AI will likely require energy-efficient deep neural networks. Brain-inspired spiking neural networks (SNN) has been identified to be a promising candidate. Doing away with the need for multipliers significantly reduces energy. For on-device applications, besides computation, communication also incurs a significant amount of energy and time. In this paper, we propose Shenjing, a configurable SNN architecture which fully exposes all on-chip communications to software, enabling software mapping of SNN models with high accuracy at low power. Unlike prior SNN architectures like TrueNorth, Shenjing does not require any model modification and retraining for the mapping. We show that conventional artificial neural networks (ANN) such as multilayer perceptron, convolutional neural networks, as well as the latest residual neural networks can be mapped successfully onto Shenjing, realizing ANNs with SNN's energy efficiency. For the MNIST inference problem using a multilayer perceptron, we were able to achieve an accuracy of 96% while consuming just 1.26mW using 10 Shenjing cores.

The topic of provable deep neural network robustness has raised considerable interest in recent years. Most research has focused on adversarial robustness, which studies the robustness of perceptive models in the neighbourhood of particular samples. However, other works have proved global properties of smaller neural networks. Yet, formally verifying perception remains uncharted. This is due notably to the lack of relevant properties to verify, as the distribution of possible inputs cannot be formally specified. We propose to take advantage of the simulators often used either to train machine learning models or to check them with statistical tests, a growing trend in industry. Our formulation allows us to formally express and verify safety properties on perception units, covering all cases that could ever be generated by the simulator, to the difference of statistical tests which cover only seen examples. Along with this theoretical formulation , we provide a tool to translate deep learning models into standard logical formulae. As a proof of concept, we train a toy example mimicking an autonomous car perceptive unit, and we formally verify that it will never fail to capture the relevant information in the provided inputs.

In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent systems, the interactions between agents often happen locally, which means that agents neither need to coordinate with all other agents nor need to coordinate with others all the time. Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents. However, the methods cannot be directly used in a large-scale environment due to the difficulty of transforming the complex interactions between agents into rules. In this paper, we model the relationship between agents by a complete graph and propose a novel game abstraction mechanism based on two-stage attention network (G2ANet), which can indicate whether there is an interaction between two agents and the importance of the interaction. We integrate this detection mechanism into graph neural network-based multi-agent reinforcement learning for conducting game abstraction and propose two novel learning algorithms GA-Comm and GA-AC. We conduct experiments in Traffic Junction and Predator-Prey. The results indicate that the proposed methods can simplify the learning process and meanwhile get better asymptotic performance compared with state-of-the-art algorithms.

Human conversations in real scenarios are complicated and building a human-like dialogue agent is an extremely challenging task. With the rapid development of deep learning techniques, data-driven models become more and more prevalent which need a huge amount of real conversation data. In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. The dataset reflects several characteristics of human-human conversations, e.g., goal-driven, and long-term dependency among the context. It also covers various dialogue types including task-oriented, chitchat and question-answering. Extra intent information and three well-annotated challenge sets are also provided. Then, we evaluate several retrieval-based and generative models to provide basic benchmark performance on JDDC corpus. And we hope JDDC can serve as an effective testbed and benefit the development of fundamental research in dialogue task.

To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans. Over the past hundred years, there has been an abundance of attempts to define and measure intelligence, across both the fields of psychology and AI. We summarize and critically assess these definitions and evaluation approaches, while making apparent the two historical conceptions of intelligence that have implicitly guided them. We note that in practice, the contemporary AI community still gravitates towards benchmarking intelligence by comparing the skill exhibited by AIs and humans at specific tasks such as board games and video games. We argue that solely measuring skill at any given task falls short of measuring intelligence, because skill is heavily modulated by prior knowledge and experience: unlimited priors or unlimited training data allow experimenters to "buy" arbitrary levels of skills for a system, in a way that masks the system's own generalization power. We then articulate a new formal definition of intelligence based on Algorithmic Information Theory, describing intelligence as skill-acquisition efficiency and highlighting the concepts of scope, generalization difficulty, priors, and experience. Using this definition, we propose a set of guidelines for what a general AI benchmark should look like. Finally, we present a benchmark closely following these guidelines, the Abstraction and Reasoning Corpus (ARC), built upon an explicit set of priors designed to be as close as possible to innate human priors. We argue that ARC can be used to measure a human-like form of general fluid intelligence and that it enables fair general intelligence comparisons between AI systems and humans.

New York City, NY: October 25, 2019 – Published via (WiredRelease) – Global (United States, European Union and China) Cognitive Computing Market Research Report 2019-2028. The Cognitive Computing Market report covers all the minute details related to the industry like Technological Developments, Growth Opportunities, Threats to Market Growth, Innovative Strategies and Futuristic Market Trends. Cognitive Computing market report provides a comprehensive overview of current trends and new product development in the global Cognitive Computing market. Featuring global and regional data and over top key players profiles, this report provides the ultimate guide to exploring opportunities in the keyword industry internationally. Some of the key players in the market are, Statistical Analysis System (SAS) Software Ltd, Saffron Technology Inc, Vicarious FPC Inc, IBM corporation, Enterra Solutions LLC, Oracle corporation, SAP Inc, Google LLC, Palantir Technologies Inc and Microsoft corporation.

"If you buy a Tesla today, I believe you're buying an appreciating asset, not a depreciating asset." Think about that statement for a second…you're buying an appreciating asset, not a depreciating asset. And what is driving the appreciation of that asset? Tesla cars become "smarter" and consequently more valuable with every mile each of the 400,000 Autopilot-equipped cars are driven. Imagine a mindset of leveraging Deep Reinforcement Learning with new operational data to create products (vehicles, trains, cranes, compressors, chillers, turbines, drills) that appreciate with usage because the products are getting more reliable, more predictive, more efficient, more effective, safer and consequently more valuable.

There's a good chance the students you're teaching today will enroll in university courses that haven't yet been created and enter jobs that don't exist. And they'll be called upon to solve some of the world's most pressing environmental, social and economic issues. We know that can feel like a lot on your shoulders, but there is plenty you can do to prepare students for success and we're here to help. Thoughtfully designed and well implemented STEM instruction builds subject-specific knowledge and fosters a growth mindset, collaboration, critical thinking and computational thinking – all vital skills for jobs of the future. We have tips to share about fun ways to participate in Hour of Code, available in Minecraft: Education Edition as a free coding lesson.

When candidates shortlisted for the strategic digital coordinator position at Sweden's Upplands-Bro Municipality showed up for their job interview in June, a 16-inch tall robot head called Tengai warmly greeted them. Sitting at eye-level on a table across the candidates, it blinked lightly and began the interview with a smile. It posed questions such as, "Can you describe a situation where you were faced with a problem that you needed to solve on your own?" Tengai could listen, speak, and react to candidates' answers while maintaining eye contact with them, thanks to its real-time visual tracking system. Occasionally, it would tilt its head, say "hmm" or lift the corners of its mouth into a smile during the interaction. "Upplands-Bro Municipality is the first employer in the world to use a social artificial intelligence-powered robot in the hiring process," says Elin Öberg Mårtenzon, chief innovation officer at TNG, the recruitment company behind Tengai.

ABOUT THE TALK: For many years, the main goal of the Netflix personalized recommendation system has been to get the right titles in front each of our members at the right time. But the job of recommendation does not end there. The homepage should be able to convey to the member enough evidence of why this is a good title for her, especially for shows that the member has never heard of. One way to address this challenge is to personalize the way we portray the titles on our service. Our image personalization engine is driven by online learning and contextual bandits.