Understanding state-of-the-art material classiﬁcation through deep visualization
Item TypeGraduate Thesis
Neural networks (NNs) excel at solving several complex, non-linear problems in the area of supervised learning. A prominent application of these networks is image classiﬁcation. Numerous improvements over the last few decades have improved the capability of these image classiﬁers. However, neural networks are still a black-box for solving image classiﬁcation and other sophisticated tasks. A number of experiments conducted look into exactly how neural networks solve these complex problems. This paper dismantles the neural network solution, incorporating convolution layers, of a specific material classiﬁer. Several techniques are utilized to investigate the solution to this problem. These techniques look at speciﬁcally which pixels contribute to the decision made by the NN as well as a look at each neuron’s contribution to the decision. The purpose of this investigation is to understand the decision-making process of the NN and to use this knowledge to suggest improvements to the material classiﬁcation algorithm.