Expanding Convolutional Tsetlin Machine for Images with Lossless Binarization

Abstract

Deep convolutional neural networks (CNN) is known to be efficient in image classification but non-interpretable. To overcome the black box nature of CNN a derivative of the Tsetlin automata, the convolutional Tsetlin machine (CTM) which is transparent and interpretable, was developed. As CTM handles binary inputs, it is important to transform the input images into binary form with minimum information loss so that the CTM can classify them correctly and efficiently. Currently, a relatively lossy mechanism, called adaptive Gaussian thresholding, was employed for binarization. To retain as much information as possible, in this thesis, we adopt an adaptive binarization mechanism, which can offer lossless input to the CTM. In more details, we employ up to 8 bits in three colour channels and arrange them in a certain way so that the CTM can handle all bits as in-put. In addition, we can also select certain significant bits and ignore others to increase efficiency of the system. Numerical results demonstrate that the newly proposed mechanism has potential to achieve better results than those of adaptive Gaussian mechanism when enough data is given after enough training epochs. The code used for this thesisis available at the [11].