Evolution sculpts both the body plans and nervous systems of agents together over time. In contrast, in AI and robotics, a robot's body plan is usually designed by hand, and control policies are then optimized for that fixed design. The task of simultaneously co-optimizing the morphology and controller of an embodied robot has remained a challenge. In psychology, the theory of embodied cognition posits that behavior arises from a close coupling between body plan and sensorimotor control, which suggests why co-optimizing these two subsystems is so difficult: most evolutionary changes to morphology tend to adversely impact sensorimotor control, leading to an overall decrease in behavioral performance. Here, we further examine this hypothesis and demonstrate a technique for "morphological innovation protection", which temporarily reduces selection pressure on recently morphologically-changed individuals, thus enabling evolution some time to "readapt" to the new morphology with subsequent control policy mutations. We show the potential for this method to avoid local optima and converge to similar highly fit morphologies across widely varying initial conditions, while sustaining fitness improvements further into optimization. While this technique is admittedly only the first of many steps that must be taken to achieve scalable optimization of embodied machines, we hope that theoretical insight into the cause of evolutionary stagnation in current methods will help to enable the automation of robot design and behavioral training -- while simultaneously providing a testbed to investigate the theory of embodied cognition.

This is a Lesson from our Data Science for Lawyers Workshops (Moderately Advanced). We'd appreciate any Feed Back, especially from non-Lawyers!. Click here to see presentation.

Feature selection is a very important technique in machine learning.We need to be able to solve it to produce models. Feature Selection requires heuristic processes to find an optimal machine learning subset. In the previous post we discussed the brute force algorithm as well as forward selection and backward elimination which were both not a great fit. What other options are there? We can use one of the most common optimization algorithms for multi-modal fitness landscapes: evolutionary algorithms. Evolutionary algorithm is a generic optimization technique mimicking the ideas of natural evolution.

In a major step toward creating artificial life, U.S. researchers have developed a living organism that incorporates both natural and artificial DNA and is capable of creating entirely new, synthetic proteins. The work, published in the journal Nature, brings scientists closer to the development of designer proteins made to order in a laboratory. However, the team say their work is safe and say the semi-synthetic organisms cannot live outside of a laboratory. This undated photo provided by The Scripps Research Institute shows a semi-synthetic strain of E. coli bacteria that can churn out novel proteins. Scientists reported on Wednesday, Nov. 29, 2017, that they have expanded the genetic code of life and used man-made DNA to create this strain of bacteria.

Previous work by Floyd Romesberg, a chemical biologist at the Scripps Research Institute in La Jolla, California, showed that it was possible to expand the genetic alphabet of natural DNA beyond its current four letters: adenine(A), cytosine(C), guanine (G) and thymine(T).

In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate expert (or mentor), we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Computer Chess Champion. This performance gain is achieved by evolving a program that mimics the behavior of a superior expert. The resulting evaluation function of the evolved program consists of a much smaller number of parameters than the expert's. The extended experimental results provided in this paper include a report of our successful participation in the 2008 World Computer Chess Championship. In principle, our expert-driven approach could be used in a wide range of problems for which appropriate experts are available. Keywords Computer chess, Fitness evaluation, Games, Genetic algorithms, Parameter tuning 1 Introduction Since the dawn of modern computer science, game playing has posed a formidable challenge in the field of Artificial Intelligence. A preliminary version of this paper appeared in Proceedings of the 2008 Genetic and Evolutionary Computation Conference [13] and received the Best Paper Award in the conference's Real-World Applications track. John McCarthy, Ken Thompson, Herbert Simon, and others) developed game-playing programs and used games in AI research. The ongoing key role played by and the impact of computer games on AI should not be underestimated.

This paper demonstrates the use of genetic algorithms for evolving a grandmaster-level evaluation function for a chess program. This is achieved by combining supervised and unsupervised learning. In the supervised learning phase the organisms are evolved to mimic the behavior of human grandmasters, and in the unsupervised learning phase these evolved organisms are further improved upon by means of coevolution. While past attempts succeeded in creating a grandmaster-level program by mimicking the behavior of existing computer chess programs, this paper presents the first successful attempt at evolving a state-of-the-art evaluation function by learning only from databases of games played by humans. Our results demonstrate that the evolved program outperforms a two-time World Computer Chess Champion.

In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate mentor, we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Computer Chess Champion. This performance gain is achieved by evolving a program with a smaller number of parameters in its evaluation function to mimic the behavior of a superior mentor which uses a more extensive evaluation function. In principle, our mentor-assisted approach could be used in a wide range of problems for which appropriate mentors are available.

The extinct passenger pigeon was once the most abundant bird in North America, and possibly the world. Although theory predicts that large populations will be more genetically diverse, passenger pigeon genetic diversity was surprisingly low. To investigate this disconnect, we analyzed 41 mitochondrial and 4 nuclear genomes from passenger pigeons and 2 genomes from band-tailed pigeons, which are passenger pigeons' closest living relatives. Passenger pigeons' large population size appears to have allowed for faster adaptive evolution and removal of harmful mutations, driving a huge loss in their neutral genetic diversity. These results demonstrate the effect that selection can have on a vertebrate genome and contradict results that suggested that population instability contributed to this species's surprisingly rapid extinction.

With Google turning to artificial intelligence to power its flagship search engine business, has the SEO industry been left in the dust? The old ways of testing and measuring are becoming antiquated, and industry insiders are scrambling to understand something new -- something which is more advanced than their backgrounds typically permit. The fact is, even Google engineers are having a hard time explaining how Google works anymore. With this in mind, is artificial intelligence changing the SEO industry for better or worse? And has Google's once-understood algorithm become a "runaway algorithm?"