发帖
雷达卡
遗传算法，也有翻译成基因算法的，是目前人工智能和机器学习当中的重要优化算法和应用，这是一本比较经典的专著。
Hands-On Genetic Algorithms
with Python
Applying genetic algorithms to solve real-world deep learning
and artificial intelligence problems
Eyal Wirsansky
Chapter 1, An Introduction to Genetic Algorithms, introduces genetic algorithms, their
underlying theory, and their basic principles of operation. You will then explore the
differences between genetic algorithms and traditional methods, and learn about the best
use cases for genetic algorithms.
Chapter 2, Understanding the Key Components of Genetic Algorithms, dives deeper into the
key components and the implementation details of genetic algorithms. After outlining the
basic genetic flow, you will learn about their different components and the various
implementations for each component.
Chapter 3, Using the DEAP Framework, introduces DEAP—a powerful and flexible
evolutionary computation framework capable of solving real-life problems using genetic
algorithms. You will discover how to use this framework by writing a Python program that
solves the OneMax problem—the 'Hello World' of genetic algorithms.
Chapter 4, Combinatorial Optimization, covers combinatorial optimization problems, such as
the knapsack problem, the traveling salesman problem, and the vehicle routing problem,
and how to write Python programs that solve them using genetic algorithms and the DEAP
framework.
Chapter 5, Constraint Satisfaction, introduces constraint satisfaction problems, such as the
N-Queen problem, the nurse scheduling problem, and the graph coloring problem, and
explains how to write Python programs that solve them using genetic algorithms and the
DEAP framework.
Chapter 6, Optimizing Continuous Functions, covers continuous optimization problems, and
how they can be solved by means of genetic algorithms. The examples you will use include
the optimization of the Eggholder function, Himmelblau's function, and
Simionescu's function. Along the way, you will explore the concepts of niching, sharing,
and constraint handling.
Chapter 7, Enhancing Machine Learning Models Using Feature Selection, talks about
supervised machine learning models, and explains how genetic algorithms can be used to
improve the performance of these models by selecting the best subset of features from the
input data provided.
Chapter 8, Hyperparameter Tuning of Machine Learning Models, explains how genetic
algorithms can be used to improve the performance of supervised machine learning models
by tuning the hyperparameters of the models, either by applying a genetic algorithmdriven
grid search, or by using a direct genetic search.
Chapter 9, Architecture Optimization of Deep Learning Networks, focuses on artificial neural
networks, and discovers how genetic algorithms can be used to improve the performance
of neural-based models by optimizing their network architecture. You will then learn how
to combine network architecture optimization with hyperparameter tuning.
Chapter 10, Reinforcement Learning with Genetic Algorithms, covers reinforcement learning,
and explains how genetic algorithms can be applied to reinforcement learning tasks while
solving two benchmark environments—MountainCar and CartPole— from the OpenAI
Gym toolkit.
Chapter 11, Genetic Image Reconstruction, experiments with the reconstruction of a wellknown
image using a set of semi-transparent polygons, orchestrated by genetic algorithms.
Along the way, you will gain useful experience in image processing and the relevant
Python libraries.
Chapter 12, Other Evolutionary and Bio-Inspired Computation Techniques, broadens your
horizons and gets you acquainted with several other biologically inspired problem-solving
techniques. Two of these methods—genetic programming and particle swarm
optimization—will be demonstrated using DEAP-based Python programs.
京公网安备 11010802022788号
