Читать книгу Cultural Algorithms - Robert G. Reynolds - Страница 4

1 Chapter 1Figure 1.1 Cultural Algorithm framework.Figure 1.2 An example of Maxwell's demon in action. The demon selectively le...

2 Chapter 2Figure 2.1 A sample of the CAT System displaying a visualization of the Cone...Figure 2.2 The CAT system's user interface panel.Figure 2.3 The fitness of ConesWorld visualized, with the height at any give...Figure 2.4 A small ConesWorld topography update of position only.Figure 2.5 The Knowledge Source fitness of a ConesWorld simulation undergoin...Figure 2.6 ConesWorld KS Fitness with a regular topographical update at ever...Figure 2.7 The CAT System Logistics Function.Figure 2.8 A three‐dimensional visualization of successive iterations of the...Figure 2.9 The initialization stage of the static (above) and dynamic (below...Figure 2.10 Five steps of the static (left) and dynamic (right) landscape ne...Figure 2.11 The homogeneous topologies. (a) Ring topology, (b) square topolo...Figure 2.12 Five steps of the static (left) and dynamic (right) bounding box...Figure 2.13 The KS fitnesses for the static (above) and dynamic (below) land...Figure 2.14 The span of each Knowledge Source's bounding boxes.Figure 2.15 The tension spring [1].Figure 2.16 The Knowledge Source fitnesses of the tension spring problem.

3 Chapter 3Figure 3.1 The cultural algorithm framework.Figure 3.2 Spectrum of knowledge distribution mechanisms.Figure 3.3 Cultural algorithm pseudocode.Figure 3.4 Updating the five knowledge source categories.Figure 3.5 The social fabric influence function: each of the knowledge sourc...Figure 3.6 Subcultured wheel selection process.Figure 3.7 Auction process phase 1: constructing the bidding wheels.Figure 3.8 Auction process phase 2: selecting KS for participation.Figure 3.9 Auction process phase 3: conducting the auction.Figure 3.10 Auction process phase 4: assigning influence.Figure 3.11 The cultural engine.Figure 3.12 An example landscape in two‐dimensional space (n = 2) bound by xFigure 3.13 Logistic function with characteristic A values.

4 Chapter 4Figure 4.1 Cultural Algorithm framework [2].Figure 4.2 The big picture for all Knowledge Distribution Mechanisms that ut...Figure 4.3 Integration of multiple KSs [9].Figure 4.4 Weighted Majority win in belief space through the social network ...Figure 4.5 Conducting the Auction [13].Figure 4.6 Big picture of CAT4 Algorithms.Figure 4.7 An Example Landscape in two‐dimensional space (n = 2) bound by x ...Figure 4.8 The value for Y (on the Y‐axis as a function of A (z axis) over t...Figure 4.9 CAT4 versus CAT2 standard deviation comparison.Figure 4.10 CAT4 Regression line over 50 runs for complexity, A = 1.0.Figure 4.11 CAT2 Regression line over 50 runs for complexity, A = 1.0.Figure 4.12 CAT4 Regression line over 50 runs for complexity, A = 3.35.Figure 4.13 CAT2 Regression line over 50 runs for complexity, A = 3.35.Figure 4.14 CAT4 Regression line over 50 runs for complexity, A = 3.99.Figure 4.15 CAT2 Regression line over 50 runs for complexity, A = 3.99.

5 Chapter 5Figure 5.1 Cultural Algorithm framework.Figure 5.2 Population network topologies.Figure 5.3 Spectrum of Knowledge Distribution mechanisms.Figure 5.4 Weighted Majority (WTD) Knowledge Distribution.Figure 5.5 Pseudocode for a general game mechanism for Knowledge Distributio...Figure 5.6 Forces guiding cooperation and defection component terms.Figure 5.7 The “hand” played by each player in IPD is set of the Degree of C...Figure 5.8 ConesWorld Landscape.Figure 5.9 KS distribution in a hexagonally networked population (a) initial...Figure 5.10 Sample processed image (base image: Udacity).Figure 5.11 Image processing, masking, and edge detection.Figure 5.12 Before and after optimization (base image: Udacity).

6 Chapter 6Figure 6.1 Cultural Algorithm Framework.Figure 6.2 Coauthorship Social Network: Personal network of Dr. Ziad Kobti o...Figure 6.3 The experts' network and three possible teams for the project/pap...Figure 6.4 The representation of teams for the project/paper, which requires...Figure 6.5 Comparison of the algorithms using the sum of distances for vario...Figure 6.6 Comparison of the algorithms on 50k nodes network with different ...Figure 6.7 Runtimes of the algorithms with different numbers of required ski...Figure 6.8 Social circle of Palliative care.Figure 6.9 Palliative Care Social Network: The framework is to visualize the...Figure 6.10 The representation of teams for the whole patients of a palliati...Figure 6.11 Comparing result of CA with various other algorithms for finding...

7 Chapter 7Figure 7.1 2D soccer simulation test bed.Figure 7.2 FSM for any player in the simulator.Figure 7.3 Pseudocode of basic CA.Figure 7.4 Enhanced defense through interposing the opposing player in posse...Figure 7.5 Average results for fitness value/generations.Figure 7.6 Evolution of values defining the fitness function.Figure 7.7 The average, maximum, and minimum number of goals that were recor...Figure 7.8 The average, maximum, and minimum number of goals that were recor...Figure 7.9 The average, maximum, and minimum number of goals that were recor...Figure 7.10 The average, maximum, and minimum number of goals that were reco...Figure 7.11 Difference in scoring between the different pairs of experiments...

8 Chapter 8Figure 8.1 The Three Levels of Data Analysis.Figure 8.2 Basic Pseudocode for Cultural Algorithm [2].Figure 8.3 Schemata of Cultural Algorithms.Figure 8.4 CAPSO Pseudocode.Figure 8.5 A Decision Tree of the sample tour using HD/MRE (0/100).Figure 8.6 Pareto Front for Payout (Goal 1) and Effort (Goal 2).Figure 8.7 The Pareto Front for Payout vs. Effort for the Full week in Phase...Figure 8.8 A plot of 500 tours generated in the search for the Pareto Front....Figure 8.9 Full Week, Pareto Frontier with all Three Phases.Figure 8.10 No Sundays, Pareto Frontier, with all three Phases.Figure 8.11 Mon_Tue_Wed, Pareto Frontier with all three Phases.Figure 8.12 Thur_Fri_Sat Pareto Frontier with all three Phases.Figure 8.13 Curve fitting for Payout, Effort using No Sundays in Phase I.Figure 8.14 Curve fitting using for first half of the week, Phase II.Figure 8.15 Curve fitting using for second half of the week, Phase II.Figure 8.16 F Distribution showing Acceptance and Rejection Regions.

9 Chapter 9Figure 9.1 Cultural Algorithm Schema [6].Figure 9.2 CAPSO's Pareto Front for CONSTR.Figure 9.3 CONSTR Parameters Corresponding to the Pareto Front.Figure 9.4 CONSTR Learning Curves.Figure 9.5 Proportion of each Knowledge Source within Weighted Roulette Whee...Figure 9.6 CONSTR: Number of Threads Per Run (Topographic Knowledge Source P...Figure 9.7 CAPSO's Pareto Front for SRN.Figure 9.8 SRN Parameter Values Corresponding to Pareto Front.Figure 9.9 SRN Learning Curves.Figure 9.10 SRN Knowledge Source Dominance.Figure 9.11 SRN Threads Per Run (Topographic Knowledge Progress).Figure 9.12 TNK Ideal Pareto Front.Figure 9.13 TNK Pareto Front.Figure 9.14 TNK Search Space.Figure 9.15 TNK Learning Curves.Figure 9.16 TNK Knowledge Source Dominance.Figure 9.17 TNK Number of Threads Per Run (Topographic Knowledge Source Prog...Figure 9.18 KITA Pareto Front.Figure 9.19 KITA Parameter Values.Figure 9.20 KITA Knowledge Source Scores.Figure 9.21 KITA Knowledge Source Dominance.Figure 9.22 KITA Threads Per Run (Topographic Knowledge Progress).Figure 9.23 KITA Feasible Region. (a) Feasible Region in the Decision Variab...

10 Chapter 10Figure 10.1 An Underwater Archaeological Site.Figure 10.2 Dr. John O'Shea Pictured with an Ancient Artifact.Figure 10.3 A Component‐Level Diagram of the Land Bridge Program.Figure 10.4 The Low‐Scale Top‐Level Scan of the Land Bridge Data with 16 Reg...Figure 10.5 An Example of the Scaling Sampling.Figure 10.6 The Topography Map.Figure 10.7 The Topography Map with Water Elements.Figure 10.8 An Example of Calculating Vectors.Figure 10.9 The Flow Direction Data Represented on a Map.Figure 10.10 A Visualization of the Water Object Data.Figure 10.11 A Visualization of the Vegetation Data.Figure 10.12 An Image from James Fogarty's Program.Figure 10.13 An Example of the A* Spaced Goals.Figure 10.14 An Example of the Temporal Difference in the Hotspot Finder.Figure 10.15 The Output of Samuel Dustin Stanley's Hotspot Finder.Figure 10.16 Area 1 with Superimposed Artifact Markers.Figure 10.17 A More Recent Run of the Hotspot Finder.Figure 10.18 A Visual of the Investigated Area.Figure 10.19 A Visualization of the Cultural Algorithm.Figure 10.20 The Alpena–Amberley Land Bridge Broken into Large Sections.Figure 10.21 A Collection of Possible Formations.Figure 10.22 A Diagram of the Flow of Data, Starting with the Hierarchical P...Figure 10.23 A Side‐by‐Side Display of a Single Area Viewed in Two Timescape...Figure 10.24 The Regional Sections of the Alpena–Amberley Land Bridge.Figure 10.25 The Land Bridge System on Microsoft's XNA.Figure 10.26 The Land Bridge System on Unity.Figure 10.27 A Full A* Path from Alpena to Amberley, through 14 Regions.Figure 10.28 Comparative Pseudocode of A* and A*mbush Algorithms.Figure 10.29 Image of Three Consecutive A*mbush Herds.Figure 10.30 Natural Caribou Migration Pathways as seen from Above.Figure 10.31 Dendriform A*mbush Pseudocode.Figure 10.32 An Example Dendriform A*mbush Run.Figure 10.33 An Example of a Heavily Effort Weighted Path.Figure 10.34 Three Examples of Risk.Figure 10.35 An Example of a Heavily Nutrition Weighted Path.Figure 10.36 The ERN Permutation Run Boundaries for Spring and Fall.