In its quest to develop functional -- and sometimes terrifying -- robots, Boston Dynamics has unleashed a veritable petting zoo of futuristic-looking machines. In recent years, the tech company, owned by Japan's SoftBank Group, has released videos showing dog-like robots unloading dishwashers and climbing stairs, galloping Bovidae-like creatures that can run move faster than Usain Bolt, and a mesmerizing humanoid robot that leaves some YouTube viewers convinced that a robot takeover is imminent. In its latest video, the first to surface in about five months, a Boston Dynamics robot has acquired a new form, one that resembles an emu. Despite its large size -- it's six feet tall and weighs 231 pounds -- the wheeled machine glides across a warehouse floor with ease, demonstrating its ability to pick up and move large boxes using what appear to be suction cups at the end of a long neck. It's referred to as "Handle" and, according to the company, was designed to carry up to 33 pounds while maneuvering in tight spaces.

Unsupervised learning is becoming more and more important recently. As one of its key components, the autoencoder (AE) aims to learn a latent feature representation of data which is more robust and discriminative. However, most AE based methods only focus on the reconstruction within the encoder-decoder phase, which ignores the inherent relation of data, i.e., statistical and geometrical dependence, and easily causes overfitting. In order to deal with this issue, we propose an Exclusivity Enhanced (EE) unsupervised feature learning approach to improve the conventional AE. To the best of our knowledge, our research is the first to utilize such exclusivity concept to cooperate with feature extraction within AE. Moreover, in this paper we also make some improvements to the stacked AE structure especially for the connection of different layers from decoders, this could be regarded as a weight initialization trial. The experimental results show that our proposed approach can achieve remarkable performance compared with other related methods.

Stationarity is a very general, qualitative assumption, that can be assessed on the basis of application specifics. It is thus a rather attractive assumption to base statistical analysis on, especially for problems for which less general qualitative assumptions, such as independence or finite memory, clearly fail. However, it has long been considered too general to allow for statistical inference to be made. One of the reasons for this is that rates of convergence, even of frequencies to the mean, are not available under this assumption alone. Recently, it has been shown that, while some natural and simple problems such as homogeneity, are indeed provably impossible to solve if one only assumes that the data is stationary (or stationary ergodic), many others can be solved using rather simple and intuitive algorithms. The latter problems include clustering and change point estimation. In this volume I summarize these results. The emphasis is on asymptotic consistency, since this the strongest property one can obtain assuming stationarity alone. While for most of the problems for which a solution is found this solution is algorithmically realizable, the main objective in this area of research, the objective which is only partially attained, is to understand what is possible and what is not possible to do for stationary time series. The considered problems include homogeneity testing, clustering with respect to distribution, clustering with respect to independence, change-point estimation, identity testing, and the general question of composite hypotheses testing. For the latter problem, a topological criterion for the existence of a consistent test is presented. In addition, several open questions are discussed.

This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer. Max-pooling layer discards the pose, i.e., translational and rotational relationship between the low-level features, and hence unable to capture the spatial hierarchies between low and high level features. The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer. The proposed SIFT Descriptor CNN therefore combines the feature extraction capabilities of CNN model and rotation invariance of SIFT descriptor. Experimental results on the MNIST and fashionMNIST datasets indicates reasonable improvements over conventional methods available in literature.

In most recent years, zero-shot recognition (ZSR) has gained increasing attention in machine learning and image processing fields. It aims at recognizing unseen class instances with knowledge transferred from seen classes. This is typically achieved by exploiting a pre-defined semantic feature space (FS), i.e., semantic attributes or word vectors, as a bridge to transfer knowledge between seen and unseen classes. However, due to the absence of unseen classes during training, the conventional ZSR easily suffers from domain shift and hubness problems. In this paper, we propose a novel ZSR learning framework that can handle these two issues well by adaptively adjusting semantic FS. To the best of our knowledge, our work is the first to consider the adaptive adjustment of semantic FS in ZSR. Moreover, our solution can be formulated to a more efficient framework that significantly boosts the training. Extensive experiments show the remarkable performance improvement of our model compared with other existing methods.

When Stanford announced a new artificial intelligence institute, the university said the "designers of AI must be broadly representative of humanity" and unveiled 120 faculty and tech leaders partnering on the initiative. Some were quick to notice that not a single member of this "representative" group appeared to be black. The backlash was swift, sparking discussion on the severe lack of diversity across the AI field. But the problems surrounding representation extend far beyond exclusion and prejudice in academia. Major tech corporations have launched AI "ethics" boards that not only lack diversity, but sometimes include powerful people with interests that don't align with the ethics mission.

BEIJING - People.cn, the online unit of China's influential People's Daily, is boosting its numbers of human internet censors backed by artificial intelligence to help firms vet content on apps and adverts, capitalizing on its unmatched Communist Party lineage. Demand for online censoring services provided by the Shanghai-listed People.cn has soared since last year after China tightened its already strict online censorship rules. As a unit of the People's Daily -- the ruling Communist Party's mouthpiece -- it is seen by clients as the go-to online censor. Investors concur, lifting shares in People.cn "The biggest advantage of People.cn is its precise grasp of policy trends," said An Fushuang, an independent analyst based in Shenzhen.

Spotify has launched a new offer that finally allows you to share your subscription with the most important person in your life. The feature – named "Premium Duo" – allows people to buy a cheaper subscription between two people, letting them sign up with their partner or someone else important in their life. As well as offering a way of getting a Spotify subscription more cheaply, the new deal gives people extra features that aren't usually available on the service. We'll tell you what's true. You can form your own view.

Apple has apologised over its MacBook's broken keyboards, and asked that anyone affected get in touch with the company's customer service team. Controversy has raged for years over Apple's latest keyboards, now found across its laptops, which use a mechanism that was first introduced along with the new laptops in 2016. Users complain that the "butterfly" mechanism found in those computers is prone to breaking, meaning that keys will simply stop working and their users will no longer be able to type. We'll tell you what's true. You can form your own view.

Samsung claims to have fixed one of the biggest concerns surrounding its new Galaxy Fold device. Part smartphone, part tablet, the Galaxy Fold is part of a new generation of foldable phones coming out in 2019, though secrecy still shrouding the handset has led to speculation that the device still has some issues. A recently leaked video appeared to show a visible crease down the centre of the main screen, which was said to appear after around 10,000 folds of the phone. We'll tell you what's true. You can form your own view.