Evolving Neural Networks

Genetic Algorithms in Elixir — by Sean Moriarity (98 / 101)

👈 Networking with Evolution | TOC | Where to Go Next 👉

As you learned in the first section, advancements in deep learning have fueled unprecedented advances in AI. You’ve seen instances throughout this chapter where genetic algorithms are a viable alternative to neural networks; however, genetic algorithms are also a viable tool for designing neural networks.

In Chapter 2, ​Breaking Down Genetic Algorithms​, you learned about hyperparameters. Remember, hyperparameters are the settings you choose, such as selection rate, crossover rate, and mutation rate, and not the parameters your algorithm learns. When designing neural networks, you can choose from a number of hyperparameters, such as how many neurons are in each layer or what the learning rate of an optimizer is.

Genetic algorithms are a great choice for hyperparameter optimization. Hyperparameter optimization in the context of neural networks is the practice of maximizing the performance of a neural network by tweaking the combination of hyperparameters. As you’ve seen in this book, genetic algorithms work well for optimization tasks. You can use genetic algorithms to intelligently search through a set of hyperparameters for the best combination of hyperparameters. The process of hyperparameter optimization can be long and tedious to perform by hand — so genetic algorithms are a smart choice, as they automate the process and are proven to work effectively with optimization problems.

Another application of genetic algorithms to neural networks is the field of neuroevolution. Neuroevolution is different from hyperparameter optimization in that it involves evolving not only the hyperparameters used in the neural network but also the weights and structure of the network. The NEAT algorithm is an example of this use case. NEAT stands for NeuroEvolution of Augmented Topologies. The NEAT algorithm is an algorithm for evolving a neural network using genetic algorithms.

Compared to more traditional deep learning approaches, neuroevolution is relatively understudied. Uber[37] proved in 2018 that genetic algorithms can significantly reduce the training time of neural networks.

One of the most significant works on genetic algorithms on the BEAM is Gene Sher’s Handbook of Neuroevolution Through Erlang [She12]. Sher firmly believes the BEAM is the best platform for the development of neuroevolutionary algorithms because the interaction of processes so closely mirrors the interaction of neurons in the brain.

👈 Networking with Evolution | TOC | Where to Go Next 👉

Genetic Algorithms in Elixir by Sean Moriarity can be purchased in other book formats directly from the Pragmatic Programmers. If you notice a code error or formatting mistake, please let us know here so that we can fix it.