Tham khảo tài liệu 'humanoid robots human-like machines part 16', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Neural Control of Actions Involving Different Coordinate Systems 591 so it will be activated by the selected combinations of x- and y-inputs. It will not be activated by different combinations such as . xj yh because Wijk is zero. Such a selective response is not feasible with one connectionist neuron. L W wikk V K 1 Figure 6. A Sigma-Pi neuron with non-zero weights along the diagonal will respond only to selected input combinations such as xj yj or xk yk or xi yi . This corresponds to Fig. 5 middle where Mj I has medium value A Sigma-Pi SOM Learning Algorithm The main idea for an algorithm to learn frame of reference transformations exploits that a representation of an object remains constant over time in some coordinate system while it changes in other systems. When we move our eyes a retinal object position will change with the positions of the eyes while the head-centered or body centered position of the object remains constant. In the algorithm presented in Fig. 7 we exploit this by sampling two input pairs . retinal object position and position of the eyes at two time instances but we connect both time instances by learning with the output taken from one instance with the input taken from the other. We assume that neurons on the output map layer respond invariantly while the inputs are varied. This forces them to adopt . a body centered representation. In unsupervised learning one has to devise a scheme how to activate those neurons which do not see the data the map neurons . Some form of competition is needed so that not all of these hidden neurons behave and learn the same. Winner-take-all is one of the simplest form of enforcing this competition without the use of a teacher. The algorithm uses this scheme Fig. 7 step 2 c based on the assumption that exactly one object needs to be coded. The corresponding winning unit to each data pair will have its weights modified so that they resemble these data more closely as given by the difference term .
