Disparity tuning as simulated by a neural net
نویسندگان
چکیده
منابع مشابه
Evidence for Disparity Tuning
The region of retinal disparity that is effective in maintaining binocular alignment of the eyes was investigated by measuring the horizontal fusional amplitudes for fixation targets consisting of a small central cross to which peripheral lines having various disparities were added. It was found that the addition of peripheral targets significantly facilitated binocular alignment, but only if t...
متن کاملNeural net backlash compensation with Hebbian tuning using dynamic inversion
A dynamic inversion compensation scheme is presented for backlash. The compensator uses the backstepping technique with neural networks (NN) for inverting the backlash nonlinearity in the feedforward path. Instead of a derivative, which cannot be implemented, a filtered derivative is used. Full rigorous stability proofs are given using filtered derivative. Compared with adaptive backstepping co...
متن کاملWavelike Design of Social Agents Simulated as System of Interacting Net of Neural Networks
Instead of following particles like interaction scheme between agents in the social domain, we have abandoned mechanistic and proposed conceptually wavelike approach. In fact, we assumed that the major modern capital accumulation is in the form of knowledge (information and environmental resources), which, being dimensionless according to information theory, has some similarities with energy. T...
متن کاملSelf-organization of binocular disparity tuning by reciprocal corticogeniculate interactions.
This article develops a neural model of how sharp disparity tuning can arise through experience-dependent development of cortical complex cells. This learning process clarifies how complex cells can binocularly match left and right eye image features with the same contrast polarity, yet also pool signals with opposite contrast polarities. Antagonistic rebounds between LGN ON and OFF cells and c...
متن کاملOrthogonal Simulated Annealing Algorithm for Tuning PID Controllers by Optimizing Fuzzy Neural Networks
In this paper, we formulate an optimization problem of establishing a fuzzy neural network model (FNNM) for efficiently tuning PID controllers of various test plants. An existing indirect, two-stage approach used a dominant pole assignment method with P=198 to find the corresponding PID controllers. Consequently, an adaptive neuro-fuzzy inference system (ANFIS) is used to independently train th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Biological Cybernetics
سال: 2000
ISSN: 0340-1200,1432-0770
DOI: 10.1007/s004220000146