In this setting, we only have access to the stochastic function f(x; ξ), where the random variable ξ is sampled from an underlying distribution D. The task is to optimize the expected function f(x), which in general may be nonconvex. This framework covers a wide range of problems, including the offline setting where we minimize the empirical loss over a fixed amount of data, and the online setting where data arrives sequentially. One of the most prominent applications of stochastic optimization has been in large-scale statistics and machine learning problems, such as the optimization of deep neural networks. Classical analysis in nonconvex optimization only guarantees convergence to a first-order stationary point (i.e., a point x satisfying ‖ f(x)‖ 0), which can be a local minimum, a local maximum, or a saddle point. This paper goes further, proposing an algorithm that escapes saddle points and converges to a local minimum.

Location fingerprinting using received signal strengths (RSSs) from wireless network infrastructure is one of the most popular and promising technologies for localization in an indoor environment, where there is no line-of-sight signal from the global positioning system (GPS) available [1]: For example, a vector of pairs of a service set identifier (SSID) and an RSS for a Wi-Fi access point (AP) measured at a location can be its location fingerprint. A location of a user/device then can be estimated by finding the closest match between its RSS measurement and the fingerprints of known locations in a database [2]. Note that the location fingerprinting technique does not require the installation of any new infrastructure or the modification of existing devices, but it is just based on the existing wireless infrastructure, which is its major advantage over alternative techniques. When the indoor localization is to cover a large building complex -- e.g., a big shopping mall or a university campus -- where there are lots of multistory buildings under the same management, the scalability of fingerprinting techniques becomes an important issue. The current state-of-the-art Wi-Fi fingerprinting techniques assume a hierarchical approach to the indoor localization, where the building, floor, and position (e.g., a label or coordinates) of a location are estimated in a hierarchical and sequential way using a different algorithm tailored for each task.

Facial attribute editing aims to modify either single or multiple attributes on a face image. Since it is practically infeasible to collect images with arbitrarily specified attributes for each person, the generative adversarial net (GAN) and the encoder-decoder architecture are usually incorporated to handle this task. With the encoder-decoder architecture, arbitrary attribute editing can then be conducted by decoding the latent representation of the face image conditioned on the specified attributes. A few existing methods attempt to establish attribute-independent latent representation for arbitrarily changing the attributes. However, since the attributes portray the characteristics of the face image, the attribute-independent constraint on the latent representation is excessive. Such constraint may result in information loss and unexpected distortion on the generated images (e.g. over-smoothing), especially for those identifiable attributes such as gender, race etc. Instead of imposing the attribute-independent constraint on the latent representation, we introduce an attribute classification constraint on the generated image, just requiring the correct change of the attributes. Meanwhile, reconstruction learning is introduced in order to guarantee the preservation of all other attribute-excluding details on the generated image, and adversarial learning is employed for visually realistic generation. Moreover, our method can be naturally extended to attribute intensity manipulation. Experiments on the CelebA dataset show that our method outperforms the state-of-the-arts on generating realistic attribute editing results with facial details well preserved.

Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year. Not only is the prevention of mosquito bites of paramount importance to the reduction of malaria transmission cases, but understanding in more forensic detail the interplay between malaria, mosquito vectors, vegetation, standing water and human populations is crucial to the deployment of more effective interventions. Typically the presence and detection of malaria-vectoring mosquitoes is only quantified by hand-operated insect traps or signified by the diagnosis of malaria. If we are to gather timely, large-scale data to improve this situation, we need to automate the process of mosquito detection and classification as much as possible. In this paper, we present a candidate mobile sensing system that acts as both a portable early warning device and an automatic acoustic data acquisition pipeline to help fuel scientific inquiry and policy. The machine learning algorithm that powers the mobile system achieves excellent off-line multi-species detection performance while remaining computationally efficient. Further, we have conducted preliminary live mosquito detection tests using low-cost mobile phones and achieved promising results. The deployment of this system for field usage in Southeast Asia and Africa is planned in the near future. In order to accelerate processing of field recordings and labelling of collected data, we employ a citizen science platform in conjunction with automated methods, the former implemented using the Zooniverse platform, allowing crowdsourcing on a grand scale.

Machine Learning (ML) has found it particularly useful in malware detection. However, as the malware evolves very fast, the stability of the feature extracted from malware serves as a critical issue in malware detection. Recent success of deep learning in image recognition, natural language processing, and machine translation indicate a potential solution for stabilizing the malware detection effectiveness. We present a coloR-inspired convolutional neuRal network-based AndroiD malware Detection (R2-D2), which can detect malware without extracting pre-selected features (e.g., the control-flow of op-code, classes, methods of functions and the timing they are invoked etc.) from Android apps. In particular, we develop a color representation for translating Android apps into RGB color code and transform them to a fixed-sized encoded image. After that, the encoded image is fed to convolutional neural network for automatic feature extraction and learning, reducing the expert's intervention. We have collected over 1 million malware samples and 1 million benign samples according to the data provided by Leopard Mobile Inc. from its core product Security Master (which has 623 million monthly active users and 10k new malware samples per day). It is shown that R2-D2 can effectively detect the malware. Furthermore, we keep our research results and release experiment material on http://R2D2.TWMAN.ORG if there is any update.

Sophia, who became a citizen of Saudi Arabia in October, has a face that can show expression and metal hands. Sophia's clear "skull" shows the inner working wires of the artificially intelligent brain, which functions through a Wi-Fi connection pumped with information and a cohesive vocabulary.

Believe it or not, Fisker isn't just focused on upscale electric cars. The automaker has teamed up with China's Hakim Unique Group on the Orbit, a self-driving electric shuttle tailor-made for smart cities. There aren't many details, but it's clearly taking advantage of its driverless nature: the boxy design maximizes passenger space, and there's a huge digital display that tells commuters when the shuttle departs and what its next stop will be. You wouldn't have to twiddle your thumbs wondering whether or not you'll make it on time. And unlike Fisker's projects to date, you won't be waiting forever to see an Orbit on the road.

Researchers in Singapore have built an underwater robot that looks and swims like a manta ray, using only single motors and flexible fins to propel it through water in a manner uncannily like its biological cousin. It's not the first of its kind - academics have spent years trying to mimic the wing-like movements of rays' pectoral fins - but Chew Chee Meng of the National University of Singapore says it's the first to use single motors for each fin and rely on the interplay of fluid and fin. One of nature's most efficient and graceful swimmers, manta rays have long fascinated scientists with a unique propulsion method to cruise through even turbulent seas, flapping their pectoral fins effortlessly to drive water backwards. The MandaDroid is designed after a juvenile manta ray. It measures 35 centimetres (13.8 inches) long, 63 centimetres wide (25 inches), and weighs just .7 kilograms (1.5 lbs).

There is a hint of Audrey Hepburn about her. Sophia, the brainchild of Hanson Robotics, has become something of a media darling. She, or if you prefer, it, has been wowing audiences around the world. Her seemingly sentient responses, social intelligence – albeit artificial intelligence – and quickish wit have paved the way for Sophia to become the world's first "celebradroid" (celebrity android). For sure, she is the first robot to be given a national citizenship (Saudi) and she is doing a great job of shining a light on Saudi Arabia's aspirations to diversify its economy and become a leading player in the global technology sector.

Legendary computer scientist Mark Weiser famously said, "the purpose of a computer is to help you do something else." It's a beautiful sentiment, but it hasn't come true. We live in constant contact with machines. And that contact is growing. As Ian Bogost points out in the Atlantic, we can't get enough computers in our lives.