An open problem in machine learning is whether flat minima generalize better and how to compute such minima efficiently. This is a very challenging problem. As a first step towards understanding this question we formalize it as an optimization problem with weakly interacting agents. We review appropriate background material from the theory of stochastic processes and provide insights that are relevant to practitioners. We propose an algorithmic framework for an extended stochastic gradient Langevin dynamics and illustrate its potential. The paper is written as a tutorial, and presents an alternative use of multi-agent learning. Our primary focus is on the design of algorithms for machine learning applications; however the underlying mathematical framework is suitable for the understanding of large scale systems of agent based models that are popular in the social sciences, economics and finance.

Partial domain adaptation aims to transfer knowledge from a label-rich source domain to a label-scarce target domain which relaxes the fully shared label space assumption across different domains. In this more general and practical scenario, a major challenge is how to select source instances in the shared classes across different domains for positive transfer. To address this issue, we propose a Domain Adversarial Reinforcement Learning (DARL) framework to automatically select source instances in the shared classes for circumventing negative transfer as well as to simultaneously learn transferable features between domains by reducing the domain shift. Specifically, in this framework, we employ deep Q-learning to learn policies for an agent to make selection decisions by approximating the action-value function. Moreover, domain adversarial learning is introduced to learn domain-invariant features for the selected source instances by the agent and the target instances, and also to determine rewards for the agent based on how relevant the selected source instances are to the target domain. Experiments on several benchmark datasets demonstrate that the superior performance of our DARL method over existing state of the arts for partial domain adaptation.

Network slicing is a key technology in 5G communications system, which aims to dynamically and efficiently allocate resources for diversified services with distinct requirements over a common underlying physical infrastructure. Therein, demand-aware allocation is of significant importance to network slicing. In this paper, we consider a scenario that contains several slices in one base station on sharing the same bandwidth. Deep reinforcement learning (DRL) is leveraged to solve this problem by regarding the varying demands and the allocated bandwidth as the environment \emph{state} and \emph{action}, respectively. In order to obtain better quality of experience (QoE) satisfaction ratio and spectrum efficiency (SE), we propose generative adversarial network (GAN) based deep distributional Q network (GAN-DDQN) to learn the distribution of state-action values. Furthermore, we estimate the distributions by approximating a full quantile function, which can make the training error more controllable. In order to protect the stability of GAN-DDQN's training process from the widely-spanning utility values, we also put forward a reward-clipping mechanism. Finally, we verify the performance of the proposed GAN-DDQN algorithm through extensive simulations.

A self-driving robot is being trialled in a Ford manufacturing plant in Spain that can overcome obstructions and carry cargo. The robot, similar in appearance to the Wall-E trash-crushing robot from Pixar, has been nicknamed'Survival' and was developed by Ford's own engineers. It uses Light Detection and Ranging (LiDAR) technology to visualise its surroundings and guides itself autonomously. Survival's body includes an automated shelf with 17 drawers of different sizes that holds various materials and tools. A self-driving robot'Survival' (pictured) is being trialled in a Ford manufacturing plant in Spain to overcome obstructions and move cargo around Its makers say that the robot is designed to work alongside human employees and not replace them.

Millions of people's private photos have been leveraged by the cloud photo service, Ever, to develop and sell facial recognition software without their consent says an exclusive report by NBC News. According to the report, Ever, which started in 2013 as a cloud-based app for storing and sharing photos, has recently started to pivot into a burgeoning field of facial recognition technology through its new arm, Ever AI. In order to train its software, which according to the company's web page, is capable of delivering'surveillance & monitoring, physical access control, and digital authentication,' it used the personal photos from its millions of its users without informing them first. According to the privacy policy and a statement from CEO of Ever, Doug Aley, the company does not distribute users' photos to third parties, but does use them to instruct its algorithm. Specifically, it leverages a facial recognition feature built into the Ever service which allows users to group photos of the same people by scanning their face.

A report from the Wall Street Journal has revealed the US is using a new type of dive-bombing'missile' that kills targets without exploding. The weapon called the R9X, or the'flying Ginsu,' is designed to crush targets by dropping through buildings and cars with the help of a six large blades that deploy seconds before impact. According to the report, the goal of the weapon is to reduce unintended casualties caused by other more standard missiles that typically detonate and engulf both targets and their surroundings. Hellfire missiles may be effective, but they often endanger innocent bystanders. The R9X or'flying Ginsu' is a weapon developed by the US military to precision-target individuals.

Blue Origin is now in the running to put Americans back on the moon by 2024. Amazon CEO Jeff Bezos has revealed the ambitious next steps for his aerospace company at a highly-secretive media event in Washington, D.C. on Thursday. During the event, which kicked off at 4 p.m., the billionaire and Blue Origin founder started off by sharing elaborate concept images of self-sustaining space habitats reminiscent of the film Interstellar, with lush greenery and futuristic homes within its walls. But, the real star of the talk turned out to be something much closer to home – the moon. On stage, Bezos took the wraps off a massive model of what will be the firm's first lunar lander, dubbed Blue Moon.

Toyota Motor Corp. and Panasonic Corp. said Thursday they will integrate their housing businesses in an expansion of an existing tie-up, as they seek to collaborate on "town development" for next-generation lifestyles where homes and vehicles are connected to the internet. The companies plan to set up a joint venture on Jan. 7, 2020. Toyota will focus on new mobility services using self-driving technology, while Panasonic brings strengths in developing smart homes equipped with appliances supported by internet and other digital technologies. The venture, Prime Life Technologies Corp., will bring housing units of both companies under its wing, including Toyota Housing Corp., Misawa Homes Co. and Panasonic Homes Co. The move by the leading carmaker and electronics manufacturer comes amid shrinking demand in the domestic housing market due to Japan's declining population.

Nike Fit will utilize smartphone cameras and augmented reality to scan users' feet and measure the full shape of both feet. If you don't know which size shoe to buy when ordering sneakers online, the world's largest shoe company is rolling out a possible solution. Nike is introducing a feature to its app that lets you scan your feet using your smartphone camera to determine what size shoe will be the perfect fit. Aptly titled, Nike Fit, the AR tool seeks to replace the steel measurement device that you find under the seats at your local shoe store. It's a timely development as more consumers shift their shopping habits online.

Erin Hawley doesn't care if she wins or loses, but with adaptive controllers, she and so many other disabled gamers are able to play the game. Gaming has been a huge part of Erin Hawley's life since she started playing Atari as a little girl. When the Keyport, New Jersey-based, 35-year-old digital content producer for the Easterseals charity gets off work, she gets right on her computer or Xbox and often keeps going until it's time for bed. Hawley is a fan of shooter titles such as "Overwatch" and "Half-Life," but she'll play adventure games, puzzles, almost anything. She's also a regular on the Amazon-owned Twitch live streaming platform.