Adapteva, a company that was on Neurdon's radar for a while, is launching their new Parallella project. The end goal is to make parallel computing, including the sort of massively parallel computing neural modelers need, both easy and cheap. And we like both... Read the rest of this entry »
-
Parallella and Adapteva
| September 28, 2012Comments: 4 Comments -
Inflatable robots
| September 22, 2012
One way in which robots will become more commonplace in our homes and working environments is by making the cheaper than today's. One of the most expensive components in a robot are actuators such as arms, which require often costly, complicated, and power-hungry designs. Annan Mozeika, Principal Robotics Engineer at iRobot Corporation, is leading his company's research efforts in inflatable robotics. Read the rest of this entry »Comments: Leave a commentCategories: Robotics -
Bringing together Biologically Inspired Vision and BMI on Mobile Robots
| August 25, 2012
God and the human brain work in mysterious ways. Imagine if we could harness the power of the brain to move objects around in the world like a telekinetic super power. Better still, imagine a patient with locked-in syndrome plus those super powers and an object recognition system that is designed to look and learn like we do! Enter CogEye, Unlock and the topic of this post. Read the rest of this entry » -
Advances in Neuromorphic Memristor Science and Applications
| August 13, 2012
This recent book, part of the Springer Series in Cognitive and Neural Systems (Editors Robert Kozma, Robinson E. Pino, and Giovanni E. Pazienza), is one that may become part of Neurdons bookshelves. In "Advances in Neuromorphic Memristor Science and Applications", the main researchers behind the pioneering work on memristors and their applications to bio-inspired machine intelligence review the state of the art and predict trends. The Abstract: Physical implementation of the memristor at industrial scale sparked the interest from various disciplines, ranging from physics, nanotechnology, electrical engineering, neuroscience, to intelligent robotics. As any promising new technology, it has raised hopes and questions; it is an extremely challenging task to live up to the high expectations and to devise revolutionary and feasible future applications for memristive devices. The possibility of gathering prominent scientists in the heart of the Silicon Valley given by the 2011 International Joint Conference on Neural Networks held in San Jose, CA, has offered us the unique opportunity of organizing a series of special events on the present status and future. Read the rest of this entry » -
Future tense
| July 26, 2012
Future Tense is a series of documentaries exploring cutting-edge technologies that will dramatically change the world we live in. The July 1st, 2012 episode was focused on Artificial Intelligence. The documentary features also the work done in the Neuromorphics Lab. Watch the trailer here and the episode below. Read the rest of this entry »Comments: 7 Comments -
Better late than never: Intel neural chips & memristors, but with a spin…
| June 18, 2012
Charles Augustine at Intel's Circuit Research Laboratory in Hillsboro, Oregon, and a few of his colleagues unveil their design for a neuromorphic chip based on memristors and spin valves. Neurdons have heard this before... Once upon a time, in a galaxy far, far away.... Read the rest of this entry »Comments: 4 Comments -
Object recognition in mobile robots
| June 15, 2012
If you want to design robots able to interact to the real world in a useful way, you will eventually bump into the problem of implementing robust object recognition, when by robust I mean able to recognize objects irrespective of (or at least able to tolerate variation in..) distance from the object, its orientation, illumination conditions, etc. This post describes work done the Neuromorphics Lab, using the Cog Ex Machina software platform to recognize objects in an iRobot Create platform. Read the rest of this entry »
Comments: Leave a comment -
Open sourcing AI & Robotics
| May 5, 2012
A guest post on the IEEE Spectrum Automation blog by author William Hertling discusses how the open source culture can revolutionize the future of robotics and AI. In both academic and industrial community, the idea of a slow, incremental progress in challenging fields such as machine perception and robotics is the standard way of thinking. May be we should think again, suggests Hertling Read the rest of this entry » -
Reinforcement Learning with Trace Conditioning
| March 14, 2012
In the previous post, I introduced the project undertaken last semester. In this post, I will go into further detail on my particular task in the project: reinforcement learning. If you recall, the robot we wish to control is an iRobot Create (a vacuumless Roomba), which we have augmented with a web camera. The camera is able to pan to 150° in either direction from center. Read the rest of this entry » -
Learning Approach/Avoidance Behaviors for Visual Stimuli
| March 12, 2012
In the fall of 2011, I, along with Jeremy Wurbs and Annan Mozeika, initiated a project to use visual tracking and reinforcement learning to cause an iRobot Create to develop approach and avoidance behaviors. This work was done for credit in Boston University's "Topics in Adaptive Mobile Robotics" course. Read the rest of this entry »
