Visualization of Machine Learning Dynamics in Tsetlin Machines

The black-box approach towards machine learning models is not helpful for creating fast and efficient implementations. optimization of these models requires a clear understanding of every aspect of the system, including the architecture, algorithms, and dynamics of the training process. This paper presents a range of visualizations for investigating the dynamics of the Tsetlin Machine, which is a new machine-learning algorithm with logic underpinning. These include static visualizations such as architecture and algorithm diagrams and dynamic visualizations such as plotting the evolution of the internal state of the machine. The workflow that supports the visualizations is generalized into an extendable open-source development kit that can be used with future generations of Tsetlin Machines. The example visualization diagrams from the MNIST dataset are discussed from the viewpoint of parallel implementation, hardware acceleration, and opportunities for architectural optimization.