Neural networks with Reinforcements

February – March, 2011
Artificial Neural Networks

At the beginning of February I implemented neuralnetworks and reinforcement learning C++ libraries which I use in my iCub application.
The most of the time I spent by implementation of the application which uses the CACLA algorithm to train iCub to reach objects.

I’m also planning to create some UML package and class diagrams to easily represent how I had designed these libraries and applications.

You can take a look at the C++ source code documentation.

I made some testing of my CACLA library on task, where I tried to move point in 3D space to some target position.

I have also read…

  • an article A Cognitive Robotic Model of Grasping, Macura et al, 2010
  • a book An Introduction to Reinforcement Learning, Sutton and Barto, 1998

I subscribed to the RobotCub forum/mailing list –

Source: Master thesis - Modelling of object grasping with neural networks in the iCub humanoid robot simulator

You might also like:

3x3 grid agent, no reciprocal connections
3x3 grid agent, no reciprocal connections
RLviaTDNN.avi
RLviaTDNN.avi
CADIE Cognitive Autoheuristic Distributed Intelligence Entity
CADIE Cognitive Autoheuristic Distributed Intelligence Entity

Stock market analysts on trial

2002-02-09 14:24:25 by on-trial

The amount of poor and self-interested advice that is being issued by brokerages and their analysts. To this day, the majority of stockbrokers are compensated on the number of trades their customers make, not on the returns they generate for them or on the quality of the advice they provide. We believe that the price targets and analyst ratings are made with several masters in mind, none of whom are the individual investor. In a similar fashion, sell-side stock analysts are generally compensated based upon the overall profitability of their firms, not the quality or accuracy of their analysis. In the end, analysts have minimal structural incentive to be accurate in their predictions; rather their built-in incentive is to be as favorable to their corporate clients as possible. It is a...

Art Levinson, Sergey Brin and Anne Wojcicki, Mark Zuckerberg and Priscilla …  — Sacramento Bee
For the genetics of neural circuits and behavior, and synaptic guidepost molecules. ... Sergey's research interests include search engines, information extraction from unstructured sources, and data mining of large text collections and scientific data ...

Related posts:

  1. Neural Networks with Java Source Code
  2. Neural networks attributes
  3. Neural Networks in the Cockpit