Herself’s Artificial Intelligence

Pyevolve was developed to be a complete genetic algorithm framework written in pure python, the main objectives of Pyevolve is:

* written in pure python, to maximize the cross-platform issue;
* easy to use API, the API must be easy for end-user;
* see the evolution, the user can and must see and interact with the evolution statistics, graphs and etc;
* extensible, the API must be extensible, the user can create new representations, genetic operators like crossover, mutation and etc;
* fast, the design must be optimized for performance;
* common features, the framework must implement the most common features: selectors like roulette wheel, tournament, ranking, uniform. Scaling schemes like linear scaling, etc;
* default parameters, we must have default operators, settings, etc in all options;
* open-source, the source is for everyone, not for only one.

More information:
Blog for Pyevolve
Documentation and downloads
GA Based Sorting using Pyevolve
MIT OpenCourseWare – Intro to Computer Science with Python

The sight of a cockroach scurrying for cover may be nauseating, but the insect is also a biological and engineering marvel, and is providing researchers at Oregon State University with what they call “bioinspiration” in a quest to build the world’s first legged robot that is capable of running effortlessly over rough terrain.

If the engineers succeed, they may owe their success to what’s being learned from these insects and other animals, such as the guinea hen, that have their own remarkable abilities.

. . .

Within certain limitations, Schmitt said, cockroaches don’t even have to think about running – they just do it, with muscle action that is instinctive and doesn’t require reflex control. That, in fact, is part of what the engineers are trying to achieve. Right now some robots have been built that can walk, but none of them can run as well as their animal counterparts. Even walking robots absorb far too much energy and computing power to be very useful.

“If we ever develop robots that can really run over rough ground, they can’t afford to use so much of their computing abilities and energy demand to accomplish it,” Schmitt said. “A cockroach doesn’t think much about running, it just runs. And it only slows down about 20 percent when going over blocks that are three times higher than its hips. That’s just remarkable, and an indication that their stability has to do with how they are built, rather than how they react.”

. . .

In a computer model, they’ve created a concept that would allow a running robot to recover from a change in ground surface almost as well as a guinea hen. They are studying how the interplay of concepts such as energy storage and expenditure, sensor and feedback requirements, and leg angles can produce recovery from such perturbations. Ultimately, a team of OSU engineers hopes to use knowledge such as this to actually build robots that can efficiently run over rough terrain without using significant computing power.

Full Press release at Oregon State

More information:
Modeling posture-dependent leg actuation in sagittal plane locomotion ( original paper )
Journal of Bioinspiration and Biomimetics ( lots of papers available at no charge )

Google’s Research Blog posted an article this week on its use of quantum computing algorithms

More information:
Training a Large Scale Classifier with the Quantum Adiabatic Algorithm
Qubuit.org, Center for Quantum Computing
Introduction to Quantum Computing
The Quantum Computer
Quantum Computing and Shor’s Algorithm
Quantum Computing Day 1, Google Tech Talk on YouTube
Quantum Computing Day 2, Google Tech Talk on YouTube
Quantum Computing Day 3, Google Tech Talk on YouTube