Abstract--The Tsetlin Machine (TM) is a novel machine learning paradigm that employs finite-state automata for learning and utilizes propositional logic to represent patterns. Due to its simplistic approach, TMs are inherently more interpretable than learning algorithms based on Neural Networks. The Con-volutional TM has shown comparable performance on various datasets such as MNIST, K-MNIST, F-MNIST and CIF AR-2. In this paper, we explore the applicability of the TM architecture for large-scale multi-channel (RGB) image classification. We propose a methodology to generate both local interpretations and global class representations. The local interpretations can be used to explain the model predictions while the global class representations aggregate important patterns for each class. These interpretations summarize the knowledge captured by the convolutional clauses, which can be visualized as images. We evaluate our methods on MNIST and CelebA datasets, using models that achieve 98.5% accuracy on MNIST and 86.56% F1-score on CelebA (compared to 88.07% for ResNet50) respectively. We show that the TM performs competitively to this deep learning model while maintaining its interpretability, even in large-scale complex training environments.

Most organizations adjust their statistical forecasts (e.g. on sales) manually. Forecasting Support Systems (FSS) enable the related process of automated forecast generation and manual adjustments. As the FSS user interface connects user and statistical algorithm, it is an obvious lever for facilitating beneficial adjustments whilst discouraging harmful adjustments. This paper reviews and organizes the literature on judgemental forecasting, forecast adjustments, and FSS design. I argue that algorithmic transparency may be a key factor towards better, integrative forecasting and test this assertion with three FSS designs that vary in their degrees of transparency based on time series decomposition. I find transparency to reduce the variance and amount of harmful forecast adjustments. Letting users adjust the algorithm's transparent components themselves, however, leads to widely varied and overall most detrimental adjustments. Responses indicate a risk of overwhelming users with algorithmic transparency without adequate training. Accordingly, self-reported satisfaction is highest with a non-transparent FSS.

Tsetlin machines (TMs) have been successful in several application domains, operating with high efficiency on Boolean representations of the input data. However, Booleanizing complex data structures such as sequences, graphs, images, signal spectra, chemical compounds, and natural language is not trivial. In this paper, we propose a hypervector (HV) based method for expressing arbitrarily large sets of concepts associated with any input data. Using a hyperdimensional space to build vectors drastically expands the capacity and flexibility of the TM. We demonstrate how images, chemical compounds, and natural language text are encoded according to the proposed method, and how the resulting HV-powered TM can achieve significantly higher accuracy and faster learning on well-known benchmarks. Our results open up a new research direction for TMs, namely how to expand and exploit the benefits of operating in hyperspace, including new booleanization strategies, optimization of TM inference and learning, as well as new TM applications.

The story begins with a short, pithy sentence: "It was nine seventeen in the morning, and the house was heavy." In clipped yet lyrical prose, the novel goes on to narrate a road trip from New York to New Orleans taken by six friends. The narrator of the novel is not one of the friends, however. It's the car itself: an artificial intelligence network on wheels equipped with a camera, a GPS, and a microphone. The various gadgets fed information into a laptop running AI software, then a printer spat out sentences--sometimes coherent, sometimes poetic--as the group glided south down the highway.

AI-written books are now an incoming reality. But can they write the next great bestseller? AI is already writing music, creating pictures for graphic novels, and winning art competitions, beating humans. One of the first experimental AI-written novels turned up as early as 2017. Called 1 the Road, it was an experiment by Ross Goodwin.

Just a few years ago, Nastacia Goodwin spent most days sitting at a computer in a lab at Smith College in Northampton, Massachusetts, stopwatch in hand, eyes fixed on three-hour long videos of prairie voles. Whenever an animal huddled close to another -- click -- she recorded the duration of their interaction. It didn't take long before Goodwin, now a graduate student in Sam Golden's research group at the University of Washington in Seattle, became eager to find a faster, less biased way to annotate videos. Machine learning was a logical choice. Goodwin co-developed Simple Behavioral Analysis, or SimBA, an open-source tool to automatically detect and classify animal behaviors from videos.

More companies are successfully exploiting predictive maintenance systems that combine AI and IoT sensors to collect data that anticipates breakdowns and recommends preventive action before break or machines fail, in a demonstration of an AI use case with proven value. This growth is reflected in optimistic market forecasts. The predictive maintenance market is sized at $6.9 billion today and is projected to grow to $28.2 billion by 2026, according to a report from IoT Analytics of Hamburg, Germany. The firm counts over 280 vendors offering solutions in the market today, projected to grow to over 500 by 2026. "This research is a wake-up call to those that claim IoT is failing," stated analyst Fernando Bruegge, author of the report, adding, "For companies that own industrial assets or sell equipment, now is the time to invest in predictive maintenance-type solutions."

Art has long been claimed as a final frontier for automation--a field seen as so ineluctably human that AI may never master it. But as robots paint self-portraits, machines overtake industries, and natural language processors write New York Times columns, this long-held belief could be on the way out. Computational literature or electronic literature--that is, literature that makes integral use of or is generated by digital technology--is hardly new. Alison Knowles used the programming language FORTRAN to write poems in 1967 and a novel allegedly written by a computer was printed as early as 1983. Universities have had digital language arts departments since at least the 90s.

Using finite-state machines to learn patterns, Tsetlin machines (TMs) have obtained competitive accuracy and learning speed across several benchmarks, with frugal memory- and energy footprint. A TM represents patterns as conjunctive clauses in propositional logic (AND-rules), each clause voting for or against a particular output. While efficient for single-output problems, one needs a separate TM per output for multi-output problems. Employing multiple TMs hinders pattern reuse because each TM then operates in a silo. In this paper, we introduce clause sharing, merging multiple TMs into a single one. Each clause is related to each output by using a weight. A positive weight makes the clause vote for output $1$, while a negative weight makes the clause vote for output $0$. The clauses thus coalesce to produce multiple outputs. The resulting coalesced Tsetlin Machine (CoTM) simultaneously learns both the weights and the composition of each clause by employing interacting Stochastic Searching on the Line (SSL) and Tsetlin Automata (TA) teams. Our empirical results on MNIST, Fashion-MNIST, and Kuzushiji-MNIST show that CoTM obtains significantly higher accuracy than TM on $50$- to $1$K-clause configurations, indicating an ability to repurpose clauses. E.g., accuracy goes from $71.99$% to $89.66$% on Fashion-MNIST when employing $50$ clauses per class (22 Kb memory). While TM and CoTM accuracy is similar when using more than $1$K clauses per class, CoTM reaches peak accuracy $3\times$ faster on MNIST with $8$K clauses. We further investigate robustness towards imbalanced training data. Our evaluations on imbalanced versions of IMDb- and CIFAR10 data show that CoTM is robust towards high degrees of class imbalance. Being able to share clauses, we believe CoTM will enable new TM application domains that involve multiple outputs, such as learning language models and auto-encoding.

Multiple federal agencies that employ law enforcement personnel used facial recognition technology designed and owned by non-government entities in recent years--and 10 deployed systems made by the controversial company, Clearview AI. In a 92-page report addressed to Congress and publicly released Tuesday, the Government Accountability Office offers details on a range of government implementations of the biometric technology. GAO Director for Homeland Security and Justice Gretta Goodwin confirmed that Reps. Jerry Nadler, D-N.Y., and Carolyn Maloney, D-N.Y., and Sens. Cory Booker, D-N.J., Chris Coons, D-Del., Edward Markey, D-Mass., and Ron Wyden D-Ore., asked GAO to steer the study. "A goal of this project was to provide the'lay of the land' in terms of federal law enforcement's use of facial recognition technology," she told Nextgov Tuesday.