If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."
However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …
As machine-learning algorithms, big data methods and artificial intelligence are increasingly used in the toolkit of U.S. law enforcement agencies, many are worrying that the existing biases of the criminal justice system are simply being automated – and deepened. Police departments are increasingly relying on predictive algorithms to figure out where to deploy their forces by blanketing cities with a mesh of human-based and computerized surveillance technology including, but not limited to, data-mining, facial recognition, and predictive policing programs. This comes despite the flaw in such tools. Facial recognition software have often held a bias toward darker-skinned individuals, including mistaking members of Congress for criminal suspects. In essence, racial profiling has become automated while allowing law enforcement agencies to claim that the computers are race-neutral tools.
Note: This article is based on a transcript of The Dr. Data Show episode, "Five Ways Your Safety Depends on Machine Learning" (click to view). Your safety depends on machine learning. This technology protects you from harm every day by guiding the maintenance of bridges, buildings, and vehicles, and by guiding healthcare providers and law enforcement officers. This puts you in good hands. Hospitals, companies, and the government use machine learning to combat risk, actively protecting you from all sorts of dangers and hazards, including fires, explosions, collapses, crashes, workplace accidents, restaurant E. coli, and crime.
The article proposes a new framework for assessment of physical rehabilitation exercises based on a deep learning approach. The objective of the framework is automated quantification of patient performance in completing prescribed rehabilitation exercises, based on captured whole-body joint trajectories. The main components of the framework are metrics for measuring movement performance, scoring functions for mapping the performance metrics into numerical scores of movement quality, and deep neural network models for regressing quality scores of input movements via supervised learning. Furthermore, an overview of the existing methods for modeling and evaluation of rehabilitation movements is presented, encompassing various distance functions, dimensionality-reduction techniques, and movement models employed for this problem in prior studies. To the best of our knowledge, this is the first work that implements deep neural network for assessment of rehabilitation performance. Multiple deep network architectures are repurposed for the task in hand and are validated on a dataset of rehabilitation exercises.
Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. AMBIDEX is a robot arm resulting from collaborative R&D on human-robot coexistence. The arm uses innovative cable-driven mechanisms that make any interaction with humans safe.
This article proposes a method for mathematical modeling of human movements related to patient exercise episodes performed during physical therapy sessions by using artificial neural networks. The generative adversarial network structure is adopted, whereby a discriminative and a generative model are trained concurrently in an adversarial manner. Different network architectures are examined, with the discriminative and generative models structured as deep subnetworks of hidden layers comprised of convolutional or recurrent computational units. The models are validated on a data set of human movements recorded with an optical motion tracker. The results demonstrate an ability of the networks for classification of new instances of motions, and for generation of motion examples that resemble the recorded motion sequences.
We study the fundamental problem of learning an unknown, smooth probability function via point-wise Bernoulli tests. We provide the first scalable algorithm for efficiently solving this problem with rigorous guarantees. In particular, we prove the convergence rate of our posterior update rule to the true probability function in L2-norm. Moreover, we allow the Bernoulli tests to depend on contextual features, and provide a modified inference engine with provable guarantees for this novel setting. Numerical results show that the empirical convergence rates match the theory, and illustrate the superiority of our approach in handling contextual features over the state-of-the-art.
Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. ESA astronaut Alexander Gerst welcomed a new face to the Columbus laboratory, thanks to the successful commissioning of technology demonstration Cimon. Short for Crew Interactive Mobile CompanioN, Cimon is a 3D-printed plastic sphere designed to test human-machine interaction in space.
The film Robot and Frank imagined a near-future where robots could do almost everything humans could. The elderly title character was given a "robot butler" to help him continue living on his own. The robot was capable of everything from cooking and cleaning to socialising (and, it turned out, burglary). This kind of science fiction may turn out to be remarkably prescient. As growing numbers of elderly people require care, researchers believe that robots could be one way to address the overwhelming demand.
More than one billion people live in slums around the world. In some developing countries, slum residents make up for more than half of the population and lack reliable sanitation services, clean water, electricity, other basic services. Thus, slum rehabilitation and improvement is an important global challenge, and a significant amount of effort and resources have been put into this endeavor. These initiatives rely heavily on slum mapping and monitoring, and it is essential to have robust and efficient methods for mapping and monitoring existing slum settlements. In this work, we introduce an approach to segment and map individual slums from satellite imagery, leveraging regional convolutional neural networks for instance segmentation using transfer learning. In addition, we also introduce a method to perform change detection and monitor slum change over time. We show that our approach effectively learns slum shape and appearance, and demonstrates strong quantitative results, resulting in a maximum AP of 80.0.
Robotic devices for clinical rehabilitation of patients with neurological impairments come in a wide variety of shapes and sizes and employ different kinds of actuators. The design process for rehabilitation robots is driven by the intention that the technical system will be paired with a human being; it is of paramount importance that safety and flexibility of operation are ensured. When designing a robotic device for people with paretic limbs it is usually desirable to specify the actuators and controllers in such a way that a degree of compliance and yielding is retained, rather than forcing the limbs to rigidly follow a pre-programmed trajectory. This reduces the likelihood of injury which might result from forcing a stiff joint to move in a non-physiological manner, and it allows the patient to positively interact with the system and actively guide the therapy. It is not uncommon to come across the viewpoint that electric actuators are not well suited to applications having compliant design requirements: in traditional control engineering, DC motors are programmed to provide accurate and fast setpoint tracking; it is often thought that they are not ideally suited for clinical rehabilitation tasks where "soft" behavioural characteristics are called for.