|
Robotic Artificial Intelligence
Robotic Artificial Intelligence -
eVision Systems Robotic platforms incorporates Genetic Algorithms, Neural Networks and Fuzzy logic Inference engines enabling dynamic autonomous learning Robots. Artificial Intelligence deployed with robust machine and parallel processing is the foundation to truly intelligent machines. eVision Systems various AI topologies are listed below and utilized thought robotic development.
Neuro-Fuzzy - The coactive neuro-fuzzy inference system (CANFIS) model integrates fuzzy inputs with a neural network to quickly solve poorly defined problems. Fuzzy inference systems are also valuable as they combine the explanatory nature of rules (membership functions) with the power of neural networks.
Support Vector Machine - The Support Vector Machine (SVM) model maps inputs to a high-dimensional feature space, and then optimally separates data into their respective classes by isolating those inputs that fall close to the data boundaries. They are especially effective in separating sets of data that share complex boundaries.
Levenberg-Marquardt - This second-order learning algorithm generally trains significantly faster than Momentum learning and usually arrives at a solution with a significantly lower error.
Conjugate Gradient - Conjugate gradient learning is a second-order training method that provides an excellent trade-off between complexity and performance. Typically it trains faster and better (lower MSE) than standard back propagation. In addition, it is completely parameterless -- no learning rates or momentum terms to adjust.
Teacher Forcing / Iterative Prediction - There are some time-series prediction problems that are best modeled using a method called teacher forcing. This specialized training algorithm feeds the predicted output back into the input in order to improve the accuracy of multi-step prediction. The predicted output of networks trained with teacher forcing is then obtained using iterative prediction.
Temporal Neural Networks
Back propagation through time (BPTT). BPTT maps a series of inputs to a series of outputs. This provides the ability to solve temporal problems by extracting how data changes over time. Examples of temporal problems are digital signal processing, speech recognition, and time-series prediction.
Problem Specific Neural Topologies
Capabilities to build hybrid neural networks based on the concept that neural networks can be broken down into a fundamental set of neural components. Individually these components are relatively simplistic, but several components connected together can result in networks capable of solving very complex problems.
Genetic Optimization
Genetic Optimization allows you to optimize virtually any parameter in a neural network to produce the lowest error. For example, the number of hidden units, the learning rates, and the input selection can all be optimized to improve the network performance. Individual weights used in the neural network can even be updated through Genetic Optimization as an alternative to traditional training methods.
| 
