|
|
|
||
Implementation methods and techniques of neural network models. Backpropagation. Boosting learning efficiency, related and advanced models. Model, topology and network size selection. Adaptive strategies of net optimization. Seminars are devoted to practical issues of specific applications implementation.
Last update: T_KSI (15.04.2003)
|
|
||
To learn methods and techniques of implementation of basic models of neuron networks Last update: Božovský Petr, RNDr., CSc. (07.04.2018)
|
|
||
Student gains a credit after a successful presentation of working programs for the tasks discussed in the course. These programs must be the student's own work, with an eventual utilization of appropriate framework that is under lecturer's approval.
As an integral part of gaining the credit, a sufficient attendance at the seminar is also considered since the task analysis and related discussion take place there. Last update: Božovský Petr, RNDr., CSc. (16.10.2017)
|
|
||
Beale R.: Neural Computing - An Introduction. Adam Hilger, Bristol, 1990 Goles E.: Lyapunov functions associated to automata networks, in Automata networks in computer science, Princeton University Press, 1987 Tank D., Hopfield J.: Simple "Neural" Optimization Networks, IEEE TCS CAS-33, pp.533-541, 1986 Last update: G_I (28.05.2004)
|
|
||
The examination is in oral form. Student has an opportunity to prepare written notes within the exam to support the oral examination.
Requirements for the examination correspond to the syllabus of the course in the range presented at the lecture. Last update: Božovský Petr, RNDr., CSc. (16.10.2017)
|
|
||
Implementation methods and techniques of neural network models. Backpropagation. Boosting learning efficiency, related and advanced models. Model, topology and network size selection. Adaptive strategies of net optimization. Seminars are devoted to practical issues of specific applications implementation. Last update: T_KSI (15.04.2003)
|