An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematical programming principle. In the perspective of brain inspiration, reinforcement learning has gained additional interest in solving decision-making tasks as increasing neuroscientific research demonstrates that significant links exist between reinforcement learning and specific neural substrates. Because of the tremendous research that focuses on human brains and reinforcement learning, scientists have investigated how robots can autonomously tackle complex tasks in the form of a self-driving agent control in a human-like way. In this study, we propose an end-to-end architecture using novel deep-Q-network architecture in conjunction with a recurrence to resolve the problem in the field of simulated self-driving. The main contribution of this study is that we trained the driving agent using a brain-inspired trial-and-error technique, which was in line with the real world situation. Besides, there are three innovations in the proposed learning network: raw screen outputs are the only information which the driving agent can rely on, a weighted layer that enhances the differences of the lengthy episode, and a modified replay mechanism that overcomes the problem of sparsity and accelerates learning. The proposed network was trained and tested under a third-partied OpenAI Gym environment. After training for several episodes, the resulting driving agent performed advanced behaviors in the given scene. We hope that in the future, the proposed brain-inspired learning system would inspire practicable self-driving control solutions.

Question answering over knowledge base (KB-QA) has recently become a popular research topic in NLP. One popular way to solve the KB-QA problem is to make use of a pipeline of several NLP modules, including entity discovery and linking (EDL) and relation detection. Recent success on KB-QA task usually involves complex network structures with sophisticated heuristics. Inspired by a previous work that builds a strong KB-QA baseline, we propose a simple but general neural model composed of fixed-size ordinally forgetting encoding (FOFE) and deep neural networks, called FOFE-net to solve KB-QA problem at different stages. For evaluation, we use two popular KB-QA datasets, SimpleQuestions and WebQSP, and a newly created dataset, FreebaseQA. The experimental results show that FOFE-net performs well on KB-QA subtasks, entity discovery and linking (EDL) and relation detection, and in turn pushing overall KB-QA system to achieve strong results on all datasets.

Google has set up an external AI ethics council to guide the tech giant away from morally questionable uses of its technology and encroaching on the privacy of its customers. It will advise the search giant on matters relating to the development and application of its artificial intelligence research. Google has been embroiled in past controversies regarding the use of its AI, as well as the way it protects the data it gathers. It established an internal AI ethics board in 2014 when it acquired DeepMind but this has been shrouded in secrecy with no details ever released about who it includes. The firm is a world-leader in many aspects of AI and the eight people recruited for the advisory board will'consider some of Google's most complex challenges'.

Video: Getting started with artificial intelligence and machine learning It depends who you ask. Back in the 1950s, the fathers of the field Minsky andMcCarthy, described artificial intelligence as any task performed by a program or a machine that, if a human carried out the same activity, we would say the human had to apply intelligence to accomplish the task. That obviously is a fairly broad definition, which is why you will sometimes see arguments over whether something is truly AI or not. AI systems will typically demonstrate at least some of the following behaviors associated with human intelligence: planning, learning, reasoning, problem solving, knowledge representation, perception, motion, and manipulation and, to a lesser extent, social intelligence and creativity. AI is ubiquitous today, used to recommend what you should buy next online, to recognise what you say to virtual assistants such as Amazon's Alexa and Apple's Siri, to recognise who and what is in a photo, to spot spam, or detect credit card fraud. At a very high level artificial intelligence can be split into two broad types: narrow AI and general AI. Narrow AI is what we see all around us in computers today: intelligent systems that have been taught or learned how to carry out specific tasks without being explicitly programmed how to do so.

British-born artificial intelligence (AI) expert Geoffrey Hinton has won the Turing Award, sometimes referred to as "the Nobel Prize of computing". Mr Hinton, who now lives in Canada, shares the award with Yoshua Bengio and Yann LeCun - two other proponents of deep learning, a popular form of AI. "The three of us have been the people who most believed in this approach," he told BBC News. "It's very nice to be recognised now that it is fashionable." A deep neural network uses many layers of artificial neurons, loosely mimicking the structure of animal brains. Such AI is increasingly used in products that people use every day - from smart speakers to Facebook.

Amazon wants to make it easier to get AI-powered apps up and running on Amazon Web Services. Toward that end, it today launched AWS Deep Learning Containers, a library of Docker images preinstalled with popular deep learning frameworks. "We've done all the hard work of building, compiling, and generating, configuring, optimizing all of these frameworks, so you don't have to," Dr. Matt Wood, general manager of deep learning and AI at AWS, said onstage at the AWS Summit in Santa Clara this morning. "And that means that you do less of the undifferentiated heavy lifting of installing these very, very complicated frameworks and then maintaining them." The new AWS container images in question -- which are preconfigured and validated by Amazon -- support Google's TensorFlow machine learning framework and Apache MXNet, with Facebook's PyTorch and other deep learning frameworks to come.

A novice painter might set brush to canvas aiming to create a stunning sunset landscape -- craggy, snow-covered peaks reflected in a glassy lake -- only to end up with something that looks more like a multi-colored inkblot. But a deep learning model developed by NVIDIA Research can do just the opposite: it turns rough doodles into photorealistic masterpieces with breathtaking ease. The tool leverages generative adversarial networks, or GANs, to convert segmentation maps into lifelike images. The interactive app using the model, in a lighthearted nod to the post-Impressionist painter, has been christened GauGAN. GauGAN could offer a powerful tool for creating virtual worlds to everyone from architects and urban planners to landscape designers and game developers.

Meta-learning methods leverage past experience to learn data-driven inductive biases from related problems, increasing learning efficiency on new tasks. This ability renders them particularly suitable for sequential decision making with limited experience. Within this problem family, we argue for the use of such approaches in the study of model-based approaches to Bayesian Optimisation, contextual bandits and Reinforcement Learning. We approach the problem by learning distributions over functions using Neural Processes (NPs), a recently introduced probabilistic meta-learning method. This allows the treatment of model uncertainty to tackle the exploration/exploitation dilemma. We show that NPs are suitable for sequential decision making on a diverse set of domains, including adversarial task search, recommender systems and model-based reinforcement learning.

Running hydrodynamical simulations to produce mock data of large-scale structure and baryonic probes, such as the thermal Sunyaev-Zeldovich (tSZ) effect, at cosmological scales is computationally challenging. We propose to leverage the expressive power of deep generative models to find an effective description of the large-scale gas distribution and temperature. We train two deep generative models, a variational auto-encoder and a generative adversarial network, on pairs of matter density and pressure slices from the BAHAMAS hydrodynamical simulation. The trained models are able to successfully map matter density to the corresponding gas pressure. We then apply the trained models on 100 lines-of-sight from SLICS, a suite of N-body simulations optimised for weak lensing covariance estimation, to generate maps of the tSZ effect. The generated tSZ maps are found to be statistically consistent with those from BAHAMAS. We conclude by considering a specific observable, the angular cross-power spectrum between the weak lensing convergence and the tSZ effect and its variance, where we find excellent agreement between the predictions from BAHAMAS and SLICS, thus enabling the use of SLICS for tSZ covariance estimation.

Kriging is the predominant method used for spatial prediction, but relies on the assumption that predictions are linear combinations of the observations. Kriging often also relies on additional assumptions such as normality and stationarity. We propose a more flexible spatial prediction method based on the Nearest-Neighbor Neural Network (4N) process that embeds deep learning into a geostatistical model. We show that the 4N process is a valid stochastic process and propose a series of new ways to construct features to be used as inputs to the deep learning model based on neighboring information. Our model framework outperforms some existing state-of-art geostatistical modelling methods for simulated non-Gaussian data and is applied to a massive forestry dataset. GPs are used directly to model Gaussian data and as the basis of non-Gaussian models such as generalized linear (e.g., Diggle et al., 1998), quantile regression (e.g., Lum et al., 2012; Reich, 2012) and spatial extremes (e.g., Cooley et al., 2007; Sang and Gelfand, 2010) models. Similarly, Kriging is the standard method for geostatistical prediction.