Open Access. Powered by Scholars. Published by Universities.®
- Keyword
- Publication
- Publication Type
Articles 1 - 2 of 2
Full-Text Articles in Computer Engineering
Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson
Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson
Electrical and Computer Engineering Faculty Publications and Presentations
"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only.
Derivation Of Equations Of Motion For A Four Link Robotic Leg For A Walking Vehicle, Andrew B. Wright
Derivation Of Equations Of Motion For A Four Link Robotic Leg For A Walking Vehicle, Andrew B. Wright
Journal of the Arkansas Academy of Science
A four degree of freedom leg for a walking robot has been modeled using Newton's method. Unlike robot manipulators, which have a fixed base, a leg model must include inertial forces due to base motion. These forces have been included in the formulation. These equations can be used for design, simulation, and control. The inverse kinematics for this leg are also presented. This allows the joint angles to be computed from a desired foot-hold position.