A Novel Neural Network-Based Symbolic Regression Method: Neuro-Encoded Expression Programming
This work addresses a bottleneck in genetic programming for symbolic regression, offering an incremental improvement by smoothing the fitness landscape to enhance search efficiency.
The paper tackled the problem of inefficient search in genetic programming for symbolic regression due to discrete, unsmooth fitness landscapes, and proposed Neuro-Encoded Expression Programming (NEEP) to address this by using a recurrent neural network for continuous encoding, resulting in improved training efficiency and reduced test errors on symbolic regression problems.
Neuro-encoded expression programming(NEEP) that aims to offer a novel continuous representation of combinatorial encoding for genetic programming methods is proposed in this paper. Genetic programming with linear representation uses nature-inspired operators (e.g., crossover, mutation) to tune expressions and finally search out the best explicit function to simulate data. The encoding mechanism is essential for genetic programmings to find a desirable solution efficiently. However, the linear representation methods manipulate the expression tree in discrete solution space, where a small change of the input can cause a large change of the output. The unsmooth landscapes destroy the local information and make difficulty in searching. The neuro-encoded expression programming constructs the gene string with recurrent neural network (RNN) and the weights of the network are optimized by powerful continuous evolutionary algorithms. The neural network mappings smoothen the sharp fitness landscape and provide rich neighborhood information to find the best expression. The experiments indicate that the novel approach improves training efficiency and reduces test errors on several well-known symbolic regression problems.