Visual Basic Developers Guide to ASP and IIS: Build Powerful Server-Side Web Applications with Visual Basic. (Visual Basic Developers Guides)

Chapter 2: Simulated Annealing

Figure 2.1: Simulated annealing algorithm.

Figure 2.2: Visualization of Acceptance Probability.

Figure 2.3: One of 92 8-Queens solutions.

Figure 2.4: N-Queens solution encoding.

Figure 2.5: Plot of sample simulated annealing run for the 40-Queens problem.

Figure 2.6: Sample Solution to the 40-Queens problem.

Chapter 3: Introduction to Adaptive Resonance Theory (ART1)

Figure 3.1: Example feature vector containing customer purchase data.

Figure 3.2: ART1 algorithm parameters.

Figure 3.3: ART1 algorithm flow.

Figure 3.4: Sample prototype and example vectors.

Figure 3.5: ART1 algorithm check on sample data from Figure 3.4.

Figure 3.6: Recommending an item using the feature vector and sum vector.

Chapter 4: Ant Algorithms

Figure 4.1: Initial configuration (T ).

Figure 4.2: One unit of time has passed (T ₁ ).

Figure 4.3: Two units of time have passed (T ₂ ).

Figure 4.4: Example of fully-connected bidirectional graph V with edge set E.

Figure 4.5: Initial configuration of the sample problem.

Figure 4.6: Simple ant tour completed.

Figure 4.7: Sample solution for the 30-city TSP.

Figure 4.8: Sample solution for the 50-city TSP.

Chapter 5: Introduction to Neural Networks and the Backpropagation Algorithm

Figure 5.1: Layered architecture for a simple brain.

Figure 5.2: Single layer perceptron.

Figure 5.3: Logic gates built from single layer perceptrons.

Figure 5.4: Multiple-layer perceptron (multi-layer network).

Figure 5.5: The sigmoid (squashing) activation function.

Figure 5.6: Hidden and output layers of a sample neural network.

Figure 5.7: Numerical backpropagation example.

Figure 5.8: Example of a neurocontroller in an environment.

Figure 5.9: Winner-take-all group .

Figure 5.10: Game AI neurocontroller architecture for verification.

Figure 5.11: Sample run of the backpropagation algorithm on the neurocontroller.

Chapter 6: Introduction to Genetic Algorithms

Figure 6.1: Encoding candidate solutions into chromosomes.

Figure 6.2: Genetic algorithm high-level flow.

Figure 6.3: Initialization of the genetic pool.

Figure 6.4: Evaluation of the population.

Figure 6.5: Selecting chromosomes based upon their fitness.

Figure 6.6: Recombining chromosomes for a new population.

Figure 6.7: Single and multi-point crossover.

Figure 6.8: Mutating a single chromosome.

Figure 6.9: Graphical plot of Equation 6.1.

Figure 6.10: Contour plot of Equation 6.1 showing z-dimension via shading.

Figure 6.11: Initial population (t ).

Figure 6.12: Fitness of initial population.

Figure 6.13: Next generation with fitness evaluated (population at t ₁ ).

Figure 6.14: Plot of fitness over time in evolving for Equation 6.5.

Chapter 7: Artificial Life

Figure 7.1: Simple food chain.

Figure 7.2: Toroid grid world for the food chain simulation.

Figure 7.3: Agent systems model.

Figure 7.4: Agent's area of perception ( facing north).

Figure 7.5: Winner-takes-all neural network as the agent brain.

Figure 7.6: Neural network for evolved herbivore.

Figure 7.7: Herbivore at time t .

Figure 7.8: Herbivore at time T ₁ .

Figure 7.9: Herbivore at time T ₂ .

Figure 7.10: Age progression in a sample simulation.

Figure 7.11: Run-time trend data from a playback simulation. Herbivore and carnivore births, while represented in the graph, are not visible due to the graph scaling and frequency of the herbivore and carnivore deaths.

Chapter 8: Introduction to Rules-Based Systems

Figure 8.1: Rules-based system illustration.

Figure 8.2: Rules-based system phases.

Figure 8.3: Graphical depiction of a blackboard architecture.

Figure 8.4: Basic flow of the rules-based system.

Figure 8.5: Format of rules within the system.

Chapter 9: Introduction to Fuzzy Logic

Figure 9.1: Quality of service scenario with rate feedback.

Figure 9.2: Membership function for packet rate.

Figure 9.3: Predator membership functions.

Figure 9.4: Predatory/prey example plot.

Figure 9.5: The fuzzy logic axioms.

Figure 9.6: Fuzzy voltage membership graph.

Figure 9.7: Fuzzy temperature membership graph.

Figure 9.8: Charge curves for the battery charge control simulation.

Chapter 10: The Bigram Model

Figure 10.1: Example Markov Chain.

Figure 10.2: Learning user interaction with an email program.

Figure 10.3: Higher level speech recognizer Markov Chain.

Figure 10.4: Sample bigram from a corpus of seven unique words.

Figure 10.5: bigramArray for the sample sentence .

Chapter 11: Agent-Based Software

Figure 11.1: Franklin and Graesser's agent taxonomy.

Figure 11.2: Providing agents with decision-making capabilities.

Figure 11.3: High-level architecture for the WebAgent.

Figure 11.4: WebAgent data flow diagram.

Figure 11.5: Sample view of the WebAgent Web page.

Figure 11.6: Sample view of WebAgent news article.

Figure 11.7: Viewing the configuration of the WebAgent.

Figure 11.8: News list example.