Data modeling using Tsetlin machines (TMs) is all about building logical rules from the data features. The decisions of the model are based on a combination of these logical rules. Hence, the model is fully transparent and it is possible to get explanations of its predictions. In this paper, we present a probability score for TM predictions and develop new techniques for uncertainty quantification to increase the explainability further. The probability score is an inherent property of any TM variant and is derived through an analysis of the TM learning dynamics. Simulated data is used to show a clear connection between the learned TM probability scores and the underlying probabilities of the data. A visualization of the probability scores also reveals that the TM is less confident in its predictions outside the training data domain, which contrasts the typical extrapolation phenomenon found in Artificial Neural Networks. The paper concludes with an application of the uncertainty quantification techniques on an image classification task using the CIFAR-10 dataset, where they provide new insights and suggest possible improvements to current TM image classification models.

Embedded Field-Programmable Gate Arrays (eFPGAs) allow for the design of hardware accelerators of edge Machine Learning (ML) applications at a lower power budget compared with traditional FPGA platforms. However, the limited eFPGA logic and memory significantly constrain compute capabilities and model size. As such, ML application deployment on eFPGAs is in direct contrast with the most recent FPGA approaches developing architecture-specific implementations and maximizing throughput over resource frugality. This paper focuses on the opposite side of this trade-off: the proposed eFPGA accelerator focuses on minimizing resource usage and allowing flexibility for on-field recalibration over throughput. This allows for runtime changes in model size, architecture, and input data dimensionality without offline resynthesis. This is made possible through the use of a bitwise compressed inference architecture of the Tsetlin Machine (TM) algorithm. TM compute does not require any multiplication operations, being limited to only bitwise AND, OR, NOT, summations and additions. Additionally, TM model compression allows the entire model to fit within the on-chip block RAM of the eFPGA. The paper uses this accelerator to propose a strategy for runtime model tuning in the field. The proposed approach uses 2.5x fewer Look-up-Tables (LUTs) and 3.38x fewer registers than the current most resource-fugal design and achieves up to 129x energy reduction compared with low-power microcontrollers running the same ML application.

System-on-Chip Field-Programmable Gate Arrays (SoC-FPGAs) offer significant throughput gains for machine learning (ML) edge inference applications via the design of co-processor accelerator systems. However, the design effort for training and translating ML models into SoC-FPGA solutions can be substantial and requires specialist knowledge aware trade-offs between model performance, power consumption, latency and resource utilization. Contrary to other ML algorithms, Tsetlin Machine (TM) performs classification by forming logic proposition between boolean actions from the Tsetlin Automata (the learning elements) and boolean input features. A trained TM model, usually, exhibits high sparsity and considerable overlapping of these logic propositions both within and among the classes. The model, thus, can be translated to RTL-level design using a miniscule number of AND and NOT gates. This paper presents MATADOR, an automated boolean-to-silicon tool with GUI interface capable of implementing optimized accelerator design of the TM model onto SoC-FPGA for inference at the edge. It offers automation of the full development pipeline: model training, system level design generation, design verification and deployment. It makes use of the logic sharing that ensues from propositional overlap and creates a compact design by effectively utilizing the TM model's sparsity. MATADOR accelerator designs are shown to be up to 13.4x faster, up to 7x more resource frugal and up to 2x more power efficient when compared to the state-of-the-art Quantized and Binary Deep Neural Network implementations.

Purpose: To utilize high-resolution quantitative CT (QCT) imaging features for prediction of diagnosis and prognosis in fibrosing interstitial lung diseases (ILD). Approach: 40 ILD patients (20 usual interstitial pneumonia (UIP), 20 non-UIP pattern ILD) were classified by expert consensus of 2 radiologists and followed for 7 years. Clinical variables were recorded. Following segmentation of the lung field, a total of 26 texture features were extracted using a lattice-based approach (TM model). The TM model was compared with previously histogram-based model (HM) for their abilities to classify UIP vs non-UIP. For prognostic assessment, survival analysis was performed comparing the expert diagnostic labels versus TM metrics. Results: In the classification analysis, the TM model outperformed the HM method with AUC of 0.70. While survival curves of UIP vs non-UIP expert labels in Cox regression analysis were not statistically different, TM QCT features allowed statistically significant partition of the cohort. Conclusions: TM model outperformed HM model in distinguishing UIP from non-UIP patterns. Most importantly, TM allows for partitioning of the cohort into distinct survival groups, whereas expert UIP vs non-UIP labeling does not. QCT TM models may improve diagnosis of ILD and offer more accurate prognostication, better guiding patient management.

This study introduces another application of software engineering tools, conceptual modeling, which can be applied to other fields of research. One way to strengthen the relationship between software engineering and other fields is to develop a good way to perform conceptual modeling that is capable of addressing the peculiarities of these fields of study. This study concentrates on humanities and social sciences, which are usually considered softer and further away from abstractions and (abstract) machines. Specifically, we focus on conceptual modeling as a software engineering tool (e.g., UML) in the area of stories and movie scripts. Researchers in the humanities and social sciences might not use the same degree of formalization that engineers do, but they still find conceptual modeling useful. Current modeling techniques (e.g., UML) fail in this task because they are geared toward the creation of software systems. Similar Conceptual Modeling Language (e.g., ConML) has been proposed with the humanities and social sciences in mind and, as claimed, can be used to model anything. This study is a venture in this direction, where a software modeling technique, Thinging Machine (TM), is applied to movie scripts and stories. The paper presents a novel approach to developing diagrammatic static/dynamic models of movie scripts and stories. The TM model diagram serves as a neutral and independent representation for narrative discourse and can be used as a communication instrument among participants. The examples presented include examples from Propp s model of fairytales; the railway children and an actual movie script seem to point to the viability of the approach.