As productivity advances, the demand of customers for multi-variety and small-batch production is increasing, thereby putting forward higher requirements for manufacturing systems. When production tasks frequent changes due to this demand, traditional manufacturing systems often cannot response promptly. The multi-agent manufacturing system is proposed to address this problem. However, because of technical limitations, the negotiation among agents in this kind of system is realized through predefined heuristic rules, which is not intelligent enough to deal with the multi-variety and small batch production. To this end, a Large Language Model-based (LLM-based) multi-agent manufacturing system for intelligent shopfloor is proposed in the present study. This system delineates the diverse agents and defines their collaborative methods. The roles of the agents encompass Machine Server Agent (MSA), Bid Inviter Agent (BIA), Bidder Agent (BA), Thinking Agent (TA), and Decision Agent (DA). Due to the support of LLMs, TA and DA acquire the ability of analyzing the shopfloor condition and choosing the most suitable machine, as opposed to executing a predefined program artificially. The negotiation between BAs and BIA is the most crucial step in connecting manufacturing resources. With the support of TA and DA, BIA will finalize the distribution of orders, relying on the information of each machine returned by BA. MSAs bears the responsibility for connecting the agents with the physical shopfloor. This system aims to distribute and transmit workpieces through the collaboration of the agents with these distinct roles, distinguishing it from other scheduling approaches. Comparative experiments were also conducted to validate the performance of this system.

Adversarial examples are malicious inputs to machine learning models that trigger a misclassification. This type of attack has been studied for close to a decade, and we find that there is a lack of study and formalization of adversary knowledge when mounting attacks. This has yielded a complex space of attack research with hard-to-compare threat models and attacks. We focus on the image classification domain and provide a theoretical framework to study adversary knowledge inspired by work in order theory. We present an adversarial example game, inspired by cryptographic games, to standardize attacks. We survey recent attacks in the image classification domain and classify their adversary's knowledge in our framework. From this systematization, we compile results that both confirm existing beliefs about adversary knowledge, such as the potency of information about the attacked model as well as allow us to derive new conclusions on the difficulty associated with the white-box and transferable threat models, for example, that transferable attacks might not be as difficult as previously thought.

Gender bias is rampant in AI systems, causing bad user experience, injustices, and mental harm to women. School curricula fail to educate AI creators on this topic, leaving them unprepared to mitigate gender bias in AI. In this paper, we designed hands-on tutorials to raise AI creators' awareness of gender bias in AI and enhance their knowledge of sources of gender bias and debiasing techniques. The tutorials were evaluated with 18 AI creators, including AI researchers, AI industrial practitioners (i.e., developers and product managers), and students who had learned AI. Their improved awareness and knowledge demonstrated the effectiveness of our tutorials, which have the potential to complement the insufficient AI gender bias education in CS/AI courses. Based on the findings, we synthesize design implications and a rubric to guide future research, education, and design efforts.

Obesity can cause various diseases and is a serious health concern. BMI, which is currently the popular measure for judging obesity, does not accurately classify obesity; it reflects the height and weight but ignores the characteristics of an individual’s body type. In order to overcome the limitations of classifying obesity using BMI, we considered 3-dimensional (3D) measurements of the human body. The scope of our study was limited to Korean subjects. In order to expand 3D body scan data clinically, 3D body scans, Dual-energy X-ray absorptiometry, and Bioelectrical Impedance Analysis data was collected pairwise for 160 Korean subjects. A machine learning-based obesity classification framework using 3D body scan data was designed, validated through Accuracy, Recall, Precision, and F1 score, and compared with BMI and BIA. In a test dataset of 40 people, BMI had the following values: Accuracy: 0.529, Recall: 0.472, Precision: 0.458, and F1 score: 0.462, while BIA had the following values: Accuracy: 0.752, Recall: 0.742, Precision: 0.751, and F1 score: 0.739. Our proposed model had the following values: Accuracy: 0.800, Recall: 0.767, Precision: 0.842, and F1 score: 0.792. Thus, our accuracy was higher than BMI as well as BIA. Our model can be used for obesity management through 3D body scans.

Associate Professor Christopher J. Vavricka, Graduate School of Science, Technology and Innovation, Kobe University, Assistant Professor Shunsuke Takahashi, Faculty of Science and Technology, Tokyo Electric University, Michihiro Araki, Deputy Director, AI Health and Pharmaceutical Research Center, Institute of Pharmaceutical Sciences, Health and Nutrition, Kobe University A research group led by Professor Masahisa Hasunuma of the Advanced Bioengineering Research Center has succeeded in producing microorganisms for plant-derived pharmaceutical raw materials by developing a machine learning prediction model capable of discovering unknown enzymes and linking it with metabolic engineering. In the future, it is expected to accelerate the bioproduction of various useful substances, functional materials, and general-purpose chemicals. The results of this research were published in the British scientific journal Nature Communications on March 16 .With the progress of synthetic biology in recent years, microbial fermentation production of plant-derived pharmaceutical raw materials is expected. When targeting BIA, which is widely used as a raw material for analgesics, the problem was that some of the enzymes that make up the metabolic pathway were unknown. To solve the problem of enzyme discovery, we developed by biotechology a machine learning prediction model and linked it to the DBTL workflow of design ( D esign) -construction ( B uild) -evaluation ( T est) -learning ( L earn).

Bradesco expects artificial intelligence will drive a significant increase in sales via digital channels.Bradesco Brazil's second-largest private bank Bradesco will ramp up its efforts around artificial intelligence (AI) to boost sales, improve customer experience and reduce operating costs in 2019. The bank, which has a portfolio of over 71 million customers, has been working on a platform dubbed Bradesco Artificial Intelligence (BIA) over the last four years. BIA's capabilities translate into an improved customer experience across the bank's digital channels - especially the app, which today accounts for 60% of customer interactions with the bank. Currently, 90% of the bank's services are already available via the app, but sales made via mobile currently represents about 20-30% of the overall business volume. We want to increase sales in that channel," says Mauricio Minas, executive vice president at the bank, adding that the goal is to increase mobile sales to 50% this year. "A few years ago we invested in the idea that BIA would be the engine of a substantial increase in Bradesco's customer value perception.

Bradesco expects artificial intelligence will drive a significant increase in sales via digital channels.Bradesco Brazil's second-largest private bank Bradesco will ramp up its efforts around artificial intelligence (AI) to boost sales, improve customer experience and reduce operating costs in 2019. The bank, which has a portfolio of over 71 million customers, has been working on a platform dubbed Bradesco Artificial Intelligence (BIA) over the last four years. BIA's capabilities translate into an improved customer experience across the bank's digital channels – especially the app, which today accounts for 60% of customer interactions with the bank. Currently, 90% of the bank's services are already available via the app, but sales made via mobile currently represents about 20-30% of the overall business volume. We want to increase sales in that channel," says Mauricio Minas, executive vice president at the bank, adding that the goal is to increase mobile sales to 50% this year. "A few years ago we invested in the idea that BIA would be the engine of a substantial increase in Bradesco's customer value perception.

Within the Kolmogorov theory of probability, Bayes' rule allows one to perform statistical inference by relating conditional probabilities to unconditional probabilities. As we show here, however, there is a continuous set of alternative inference rules that yield the same results, and that may have computational or practical advantages for certain problems. We formulate generalized axioms for probability theory, according to which the reverse conditional probability distribution P(B|A) is not specified by the forward conditional probability distribution P(A|B) and the marginals P(A) and P(B). Thus, in order to perform statistical inference, one must specify an additional "inference axiom," which relates P(B|A) to P(A|B), P(A), and P(B). We show that when Bayes' rule is chosen as the inference axiom, the axioms are equivalent to the classical Kolmogorov axioms. We then derive consistency conditions on the inference axiom, and thereby characterize the set of all possible rules for inference. The set of "first-order" inference axioms, defined as the set of axioms in which P(B|A) depends on the first power of P(A|B), is found to be a 1-simplex, with Bayes' rule at one of the extreme points. The other extreme point, the "inversion rule," is studied in depth.

Feature selection, identifying a subset of variables that are relevant for predicting a response, is an important and challenging component of many methods in statistics and machine learning. Feature selection is especially difficult and computationally intensive when the number of variables approaches or exceeds the number of samples, as is often the case for many genomic datasets. Here, we introduce a new approach -- the Bayesian Ising Approximation (BIA) -- to rapidly calculate posterior probabilities for feature relevance in L2 penalized linear regression. In the regime where the regression problem is strongly regularized by the prior, we show that computing the marginal posterior probabilities for features is equivalent to computing the magnetizations of an Ising model. Using a mean field approximation, we show it is possible to rapidly compute the feature selection path described by the posterior probabilities as a function of the L2 penalty. We present simulations and analytical results illustrating the accuracy of the BIA on some simple regression problems. Finally, we demonstrate the applicability of the BIA to high dimensional regression by analyzing a gene expression dataset with nearly 30,000 features.

The DUCK-calculus presented here is a recent approach to cope with probabilistic uncertainty in a sound and efficient way. Uncertain rules with bounds for probabilities and explicit conditional independences can be maintained incrementally. The basic inference mechanism relies on local bounds propagation, implementable by deductive databases with a bottom-up fixpoint evaluation. In situations, where no precise bounds are deducible, it can be combined with simple operations research techniques on a local scope. In particular, we provide new precise analytical bounds for probabilistic entailment.