Zde můžete vidět rozdíly mezi vybranou verzí a aktuální verzí dané stránky.

Odkaz na výstup diff

courses:a4m33bia [2016/06/16 23:05]
matejch [2016, 2. 6.]
courses:a4m33bia [2019/01/10 18:36] (aktuální)
Řádek 204: Řádek 204:
 <​code>​ <​code>​
-1. SOM+1. Self-Organizing Maps (SOM) [3 pts] 
 +• Explain SOM network architecture and learning. 
 +• Draw the SOM for 2D input and 5x5 grid of neurons. 
 +2. Recurrent Neural Netowrk (RNN) [3 pts] 
 +• Describe fully-connected RNN architecture. 
 +• Describe evaluation and learning of RNN. 
 +• What is synchronous/​asynchronous network evaluation?​ 
 +3. Neuro-evolution [3 pts] 
 +• Discuss mutation and crossover in neuro-evolution. 
 +4. Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) [4 pts] 
 +• Describe HyperNEAT algorithm. 
 +• What is the difference between HyperNEAT and standard evolution of ANNs? 
 +5. Overfitting [4 pts] 
 +• How can you prevent overfitting of artificial neural network? 
 +6. Perceptron vs Radial Basis Function (RBF) type neurons [3 pts] 
 +• Describe differences between perceptron and RBF neurons. 
 +• Draw an illustrative picture of how they divide an input space. 
 +7. EAs for Multi-Objective Optimizations [4 pts] 
 +• Write a definition of domination. 
 +• Describe two goals of the multi-objective optimization. What are the two desired properties of the final set of solutions?​ 
 +• Lets assume a set of all feasible solution in the left figure below. Draw a complete Pareto-optimal set in the figure given the minimization objective o1 and minimization objective o2. 
 +• Lets assume the set of candidate solutions in the right figure. Draw the first four fronts of non-dominated solutions given the minimization objective o1 and minimization objective o2. 
 +{ two pictures, first figure - space, second figure - points } 
 +8. Ant Colony Optimization for Continuous Domain (ACOr) [3 pts] 
 +• Describe the ACOr algorithm 
 +• Describe the way the Gaussian kernel probabilty density function (PDF) is used to model the pheromone. 
 +• Describe how the Gaussian kernel PDF is modelled and how its parameters are estimated. 
 +9. Roulette Wheel [4 pts] 
 +• Describe the roulette wheel selection method. 
 +• Given a population of 5 individuals with the following fitness value - fitness(A)=1,​ fitness(B)=2,​ fitness(C)=3,​ fitness(D)=5,​ fitness(E)=9 - determine an expected number of copies that solution A and E recieve among ten solutions samples using a roulette wheel selection method. What is the range of the actual number of copies of A and E out of the ten samples solutions?​ 
 +10. Dynamic Optimizations [3 pts] 
 +• Desribe the principles of the GA with Real-coded Binary Representation (GARB). 
 +• Redundant representaion 
 +• Gene-strength adaptation 
 +11. Ant Colony Optmimization (ACO) [3 pts] 
 +• Describe the following formula used for probabilistic decision making in ACO algorithm. How is it used in ACO algorithm?​ 
 +• Explain a meaning of the symbols Tau, Eta, alpha, beta, tabuk. 
 +{ p_ij^k = ... formula } 
 +12. Performance Metrics for Multi-Objective Optimizations [3 pts] 
 +• Describe the S metric (i.e. the size of the space covered) used to assess a quality of a set of non-dominated solutions. 
 +• What are its advantages and disadvantages?​ 
 +• Illustrate it on an example.
 </​code>​ </​code>​
courses/a4m33bia.txt · Poslední úprava: 2019/01/10 18:36 (upraveno mimo DokuWiki)
Nahoru = chi`s home Valid CSS Driven by DokuWiki do yourself a favour and use a real browser - get firefox!! Recent changes RSS feed Valid XHTML 1.0