Recent research has revealed that the output of Deep Neural Networks (DNN) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we analyze an attack in an extremely limited scenario where only one pixel can be modified. For that we propose a novel method for generating one-pixel adversarial perturbations based on differential evolution. It requires less adversarial information and can fool more types of networks. The results show that 70.97% of the natural images can be perturbed to at least one target class by modifying just one pixel with 97.47% confidence on average. Thus, the proposed attack explores a different take on adversarial machine learning in an extreme limited scenario, showing that current DNNs are also vulnerable to such low dimension attacks.

The $L_1$-regularized models are widely used for sparse regression or classification tasks. In this paper, we propose the orthant-wise passive descent algorithm (OPDA) for optimizing $L_1$-regularized models, as an improved substitute of proximal algorithms, which are the standard tools for optimizing the models nowadays. OPDA uses a stochastic variance-reduced gradient (SVRG) to initialize the descent direction, then apply a novel alignment operator to encourage each element keeping the same sign after one iteration of update, so the parameter remains in the same orthant as before. It also explicitly suppresses the magnitude of each element to impose sparsity. The quasi-Newton update can be utilized to incorporate curvature information and accelerate the speed. We prove a linear convergence rate for OPDA on general smooth and strongly-convex loss functions. By conducting experiments on $L_1$-regularized logistic regression and convolutional neural networks, we show that OPDA outperforms state-of-the-art stochastic proximal algorithms, implying a wide range of applications in training sparse models.

We address the task of generating query suggestions for task-based search. The current state of the art relies heavily on suggestions provided by a major search engine. In this paper, we solve the task without reliance on search engines. Specifically, we focus on the first step of a two-stage pipeline approach, which is dedicated to the generation of query suggestion candidates. We present three methods for generating candidate suggestions and apply them on multiple information sources. Using a purpose-built test collection, we find that these methods are able to generate high-quality suggestion candidates.

Researchers now believe that language might have developed from cave drawings. Specifically, they think the ancient artwork located in caves with good acoustics might have inspired humans to develop the vocal communication that exists today. A new report on the theory from the Massachusetts Institute of Technology hinges on the fact that caves allow for echoes. The researchers think that previously discovered cave drawings prove that the fundamental parts of speech were derived from artwork. The MIT team that worked on the new analysis said that taking a look in the depths of ancient caves can provide modern humans with answers about where languages stemmed from.

We are on the verge of a technological revolution that will fundamentally alter the way we live, work, and relate to one another unlike anything humankind has experienced before. The main driver for this technological revolution is Artificial Intelligence (AI). Technological change driven by AI will change not only what we do but also who we are. It will affect our identity and all the issues associated with it: our sense of privacy, our notions of ownership, our consumption patterns, the time we devote to work and leisure, and how we develop our careers, cultivate our skills, and nurture relationships. But the development and applications of artificial intelligence can also present a dystopian threat to our collective and individual well being. From SIRI to self-driving cars, artificial intelligence (AI) is progressing rapidly. While science fiction often portrays AI as robots with human-like characteristics, AI can encompass anything from Google's search algorithms to IBM's Watson to autonomous robots and weapons systems. Artificial intelligence today is often referred to as narrow AI (or weak AI), which is designed to perform a narrow task (eg:facial recognition or only internet searches or driving a car). The other kind of Artificial Intelligence is termed general AI (AGI or strong AI) which is designed to "think," and solve problems much like humans.

Want to watch this again later? Sign in to add this video to a playlist. Report Need to report the video? Sign in to report inappropriate content. Report Need to report the video?

Male monkeys with large noses have more females in their harems – proving that size does matter, according to a team of scientists. Researchers studying proboscis monkeys in Malaysia found that males with exaggerated masculine traits, such as big noses, 'serve as advertisements to females in mate selection'. Those involved in the study from Cardiff University, Kyoto University and Sabah Wildlife Department and the Danau Girang Field Centre in Malaysia, say the new evidence points to both male-male competition and female choice as contributing to the evolution of enlarged male noses. Explanations for the primate s long nose have previously been gleaned more from folklore than from science. But, researchers studying proboscis monkeys in Malaysia found that big noses'serve as advertisements to females in mate selection' The primate, which is native to Borneo, sports a sizeable snout, which Dr Sen Nathan, assistant director of Sabah Wildlife Department and PhD student at Cardiff University and Danau Girang Field Centre, said had long been admired as an'extremely attractive' visual feature by biologists.

AI teaching computers to make business sense of ill-lit 3D objects. We invested in Doxel, because of Saurabh Ladha, and his co-founder Robin Singh. They are without much parallel when it comes to the tech of 3D semantic understanding, and with their team of CS PhDs essentially writing software using AI to teach computers to make sense of the 3D world around them -- even when in less than ideal, real world sites that have little to no light. Both founders come with exceptionally strong engineering backgrounds, having met on the Dubai campus and then they split off to respectively Stanford and Ann Arbor Michigan for further education. This technology has broad application to industries of any kind wanting to know what's going on on any physical project of theirs, be it construction, agriculture, shipping, manufacture and many more have been relegated to a 2D static world.

A new artificial intelligence (AI) venture from tech giant Alibaba could ease a portion of the various issues confronting Chinese farmers in the pork business. China is the world's biggest maker and consumer of pork, and monitoring the country's estimated 700 million creatures is famously troublesome for farmers. They have to give careful consideration to guarantee that piglets aren't squashed to death by their moms, sows aren't reared past their prime, and sick pigs don't pass their diseases on to the remaining populace. Right now, agriculturists track pigs by clipping wireless radio frequency identification (RFID) labels to the creatures' ears. These can be costly, and farmers don't generally have room schedule-wise to fit each pig with a tag and scan them.

Boston Dynamics' door-opening robot dog can now fight off humans. The company has published a new video that shows SpotMini, a small, four-legged robot, successfully open a door and walk through it, despite the efforts of a person armed with a hockey stick, who repeatedly tries to impede the robot. He initially attempts to prevent SpotMini's hand from reaching the door handle. When SpotMini eventually gets a good grip of it and manages to turn the handle and pull the door open, he tries to push the door shut. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph.