A long-term goal in evolutionary machine learning is to evolve compact models, which can learn effectively in complex, high dimensional domains with many noisy and irrelevant features. NeuroEvolution, the process of using evolutionary computation to evolve the topology and weights of neural networks is an effective and general approach to this. To date there has been little work using methods such as NeuroEvolution of Augmenting Topologies (NEAT), on very large, noisy datasets with up to 100,000 variables and there have been few alternative methods proposed. This paper proposes a new network called Blocky Net with built-in feature selection, and a limited maximum parameter space and complexity. This method is compared against NEAT and FS-NEAT in a supervised classification setting, using 20 diverse datasets ranging from 10 up to 100,000 features. The results show the proposed method is a valuable alternative to NEAT and FS-NEAT with better performance on 13 of the 20 datasets tested versus 2 for FS-NEAT, and is better than NEAT in all cases. The analysis also shows this minimal method of NeuroEvolution allows for a number of promising future research directions.

We present a model for the steering of programmable bevel-tip needles, along with a set of experiments demonstrating the three-dimensional steering performance of a new, clinically viable, 4-segment, preproduction prototype. A multibeam approach based on Euler-Bernoulli beam theory is used to model the novel multisegment design of these needles. Finite element (FE) simulations for known loads are used to validate the multibeam deflection model. A clinically sized (2.5 mm outer diameter), 4-segment programmable bevel-tip needle, manufactured by extrusion of a medical-grade polymer, is used to conduct an extensive set of experimental trials to evaluate the steering model. For the first time, we demonstrate the ability of the 4-segment needle design to steer in any direction with a maximum achievable curvature of (0.0192 ± 0.0014 mm-1). FE simulations confirm that the multibeam approach produces a good model fit for tip deflections, with a root-mean-square deviation (RMSD) in modeled tip deflection of 0.2636 mm. We perform a parameter optimization to produce a best-fit steering model for experimental trials with a RMSD in curvature prediction of 1.12 × 10-3mm-1.