Search

Neural networks and deep learning are changing the way that artificial intelligence is being done. Efficiently choosing a suitable network architecture and fine-tune its hyper-parameters for a specific dataset is a time-consuming task given the staggering number of possible alternatives. In this paper, we address the problem of model selection by means of a fully automated framework for efficiently selecting a neural network model for a given task: classification or regression. The algorithm, named Automatic Model Selection, is a modified micro-genetic algorithm that automatically and efficiently finds the most suitable neural network model for a given dataset. The main contributions of this method are a simple list based encoding for neural networks as genotypes in an evolutionary algorithm, new crossover, and mutation operators, the introduction of a fitness function that considers both, the accuracy of the model and its complexity and a method to measure the similarity between two neural networks. AMS is evaluated on two different datasets. By comparing some models obtained with AMS to state-of-the-art models for each dataset we show that AMS can automatically find efficient neural network models. Furthermore, AMS is computationally efficient and can make use of distributed computing paradigms to further boost its performance., Comment: 31 pages, 6 figures. Preprint Submitted to Elsevier Neural Networks

In this paper, we describe the characteristics of imagery phenomena in problem solving, develop a model for the process of forming and observing mental images in problem solving, and check the model against data obtained from subjects. Then, we describe the interaction between imaging and problem solving observed in our experiments, and discuss the use of our model to simulate it. We also discuss the relation between mental models and mental image briefly.

In this paper we discuss the role of imagery in understanding problems and the processes of using images to solve problems. On the basis of two experiments and computer simulation, we show how subjects, in solving a particular problem, form mental images to represent a changing physical state. By "running" and watching the mental Image they can draw qualitative conclusions about the situation, then derive a quantitative equation to solve the problem.

Fourteen subjects were tape recorded while they undertook to find a law to summarize numerical data they were given. The source of the data was not identified, nor were the variables labeled semantically. Unknown to the subjects, the data were measurements of the distances of the planets from the Sun and the periods of their revolutions about it -- equivalent to the data used by Johannes Kepler to discover his Third Law of planetary motion. Four of the 14 subjects discovered the same law as Kepler did (the period varies as the 3/2 power of the distance), and a fifth came very close to the answer. The subjects' protocols provide a detailed picture of the problem-solving search they engaged in, mainly, but not exclusively, in the space of possible functions for fitting the data, and provide explanations as to why some succeeded and the others failed. The search heuristics used by the subjects are similar to those embodied in the BACON program, a computer simulation of certain scientific discovery processes. Keywords: Scientific discovery; Learning; Search; Cognitive processes.