Some time ago I published a blog post with the title Know your data structures!. In this previous post I explained how I improved the running time of a genetic algorithm. The post Learning Club 16: Genetic Algorithms appeared first on verenahaunschmid.

Scientists have been studying exoskeletons in nature for years, and they've been trying to figure out how to adapt them for human use. After all, a powered exoskeleton could change the lives of people who have mobility issues, whether due to age, injury or disease. The problem is that exoskeletons aren't one size fits all. Adapting them to individual humans is a difficult and time-consuming process. But now, researchers at Carnegie Mellon University may have found a way to make it a whole lot easier.

Artificial Intelligence (AI) is everywhere these days, but it's rarely discussed in detail, or with specific examples of how and why it will help improve the way we do things. Let's address that shortcoming by digging into a particular variant of AI that holds great promise: Swarm Intelligence. Swarm Intelligence is the idea of using many simplistic machine learning models each good at one small task to solve bigger, more complex problems. The idea is analogous to how swarms or hives act in the natural world. Take ants, for example: each performs a simple task that helps that hive work as a complex system.

In this paper we investigate the convergence properties of a variant of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Our study is based on the recent theoretical foundation that the pure rank-mu update CMA-ES performs the natural gradient descent on the parameter space of Gaussian distributions. We derive a novel variant of the natural gradient method where the parameters of the Gaussian distribution are updated along the natural gradient to improve a newly defined function on the parameter space. We study this algorithm on composites of a monotone function with a convex quadratic function. We prove that our algorithm adapts the covariance matrix so that it becomes proportional to the inverse of the Hessian of the original objective function. We also show the speed of covariance matrix adaptation and the speed of convergence of the parameters. We introduce a stochastic algorithm that approximates the natural gradient with finite samples and present some simulated results to evaluate how precisely the stochastic algorithm approximates the deterministic, ideal one under finite samples and to see how similarly our algorithm and the CMA-ES perform.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

Energy costs are an increasingly important issue in real-world scheduling, for both economic and environmental reasons. This paper deals with a variant of the well-known job shop scheduling problem, where we consider a bi-objective optimization of both the weighted tardiness and the energy costs. To this end, we design a hybrid metaheuristic that combines a genetic algorithm with a novel local search method and a linear programming approach. We also propose an efficient procedure for improving the energy cost of a given schedule. In the experimental study we analyse our proposal and compare it with the state of the art and also with a constraint programming approach, obtaining competitive results.

The 119 drones underwent catapult-assisted take-offs and performed aerial formations, the Xinhua News Agency reported on Sunday. The CETC said "swarm intelligence" is regarded as the core of the artificial intelligence of unmanned systems and the future of intelligent unmanned systems. The huge scale of low cost and multi-function UAVs could be used in risky tasks such as emergency communications. CETC engineer Zhao Yanjie said since drones were invented in 1917, intelligent swarms have "changed the rules of the game." In November 2016, the CETC launched 67 drones during the China International Aviation & Aerospace Exhibition in Zhuhai, South China's Guangdong Province, breaking the previous record of 50 drones by the US Navy, CCTV reported.

The OneMax problem is a standard benchmark optimisation problem for a binary search space. Recent work on applying a Bandit-Based Random Mutation Hill-Climbing algorithm to the noisy OneMax Problem showed that it is important to choose a good value for the resampling number to make a careful trade off between taking more samples in order to reduce noise, and taking fewer samples to reduce the total computational cost. This paper extends that observation, by deriving an analytical expression for the running time of the RMHC algorithm with resampling applied to the noisy OneMax problem, and showing both theoretically and empirically that the optimal resampling number increases with the number of dimensions in the search space.

As someone so flummoxed by traffic I wrote a book about it, I have a near-clinical aversion to vehicular congestion. My global default strategy is to simply drive as little as possible, but there are times when I simply must put foot to gas pedal. Like many, I have become increasingly dependent on the Waze app, which, via each drivers' smartphone, turns an inchoate, undifferentiated mass of drivers into something resembling a collective form of networked intelligence. Waze, it occurred to me the other day while stuck in a bit of unexpected congestion (which had been duly flagged by at least 13 "Wazers"), is helping us turn into ants. Every time drivers travel down a path, Waze tracks their speed--information that can then be broadcast to every following driver.

Building on a survey of previous theories of serendipity and creativity, we advance a sequential model of serendipitous occurrences. We distinguish between serendipity as a service and serendipity in the system itself, clarify the role of invention and discovery, and provide a measure for the serendipity potential of a system. While a system can arguably not be guaranteed to be serendipitous, it can have a high potential for serendipity. Practitioners can use these theoretical tools to evaluate a computational system's potential for unexpected behaviour that may have a beneficial outcome. In addition to a qualitative features of serendipity potential, the model also includes quantitative ratings that can guide development work. We show how the model is used in three case studies of existing and hypothetical systems, in the context of evolutionary computing, automated programming, and (next-generation) recommender systems. From this analysis, we extract recommendations for practitioners working with computational serendipity, and outline future directions for research.