The Python Testbed for Federated Learning Algorithms is a simple Python FL framework that is easy to use by ML&AI developers who do not need to be professional programmers and is also amenable to LLMs. In the previous research, generic federated learning algorithms provided by this framework were manually translated into the CSP processes and algorithms' safety and liveness properties were automatically verified by the model checker PAT. In this paper, a simple translation process is introduced wherein the ChatGPT is used to automate the translation of the mentioned federated learning algorithms in Python into the corresponding CSP processes. Within the process, the minimality of the used context is estimated based on the feedback from ChatGPT. The proposed translation process was experimentally validated by successful translation (verified by the model checker PAT) of both generic centralized and decentralized federated learning algorithms.

This post - print is the paper version that was submitted to ZINC 202 5 . Abstract -- Recently, federated learning frameworks such as Python TestBed for Federated Learning Algorithms and MicroPython TestBed for Federated Learning Algorithms have emerged to tackle user privacy concerns and efficiency in embedded systems. Even more recently, an efficient federated anomaly detection algorithm, FLiForest, based on Isolation Forests has been developed, offering a low - resource, unsupervised method well - suited for edge deployment and continuous learning. In this paper, we present an appli cation of Isolation Forest - based temperature anomaly detection, developed using the previously mentioned federated learning frameworks, aimed at small edge devices and IoT systems running MicroPython. The system has been experimentally evaluated, achieving over 9 6 % accuracy in distinguishing normal from abnormal readings and above 78 % precision in detecting anomalies across all tested configurations, while maintaining a memory usage below 16 0 KB during model training.

We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a weight function to the maximum entropy framework, with the motivation of having the ability to learn and recover the stochasticity (or the bounded rationality) of the expert policy. Our framework and algorithms allow to learn both a reward (or policy) function and the structure of the entropy terms added to the Markov Decision Processes, thus enhancing the learning procedure. Our numerical experiments using human and simulated demonstrations and with discrete and continuous IRL/IM tasks show that our approach outperforms prior algorithms.

Technology has enabled new insight into ancient documents that have fascinated and often mystified scholars of Jewish and religious history since their discovery around 70 years ago. Researchers at the University of Groningen in the Netherlands used artificial intelligence to analyze the longest text of the Dead Sea Scrolls, running at 24 feet long and consuming 17 pieces of parchment. The Great Isaiah Scroll, according to the newly published research, was written by two scribes with very similar handwriting, not one author as previously thought. The Groningen study notes that those previous explanations of authorship were based on educated guesses. "We will never know their names," Mladen Popovic, one of the authors of the study, said in a statement.

One day during the second century BC, a scribe dipped a pen in ink and started writing pages and pages of Hebrew on leather parchment. The manuscript was to become one of the famous Dead Sea Scrolls. But about halfway through their job, the scribe stopped writing, and the rest of the 7-metre-long manuscript was written by someone else. Centuries later in 1947, a young Bedouin shepherd stumbled upon the scroll, which had been wrapped in linen and hidden in a jar, as part of a legendary find in the Qumran Caves west of Jerusalem. As experts examined what became known as the Great Scroll of Isaiah, they noted the handwriting appeared to be uniform throughout, and most assumed it had been scribed by one person.

Embark co-founders Alex Rodrigues, left, and Brendon Moak with their fleet of autonomous semi-trucks at the startup's operations center in Ontario, California. Embark Trucks, a robotic tech upstart led by two young Canadian computer scientists, hired a key member of Tesla's Autopilot team to help its self-driving trucks better see and understand their surroundings and highway conditions. Zeljko Popovic, an engineer with a background in robotics who joined Tesla over six years ago and created and ran the Perception Team for Autopilot, is now Perception Lead for San Francisco-based Embark, the company said. He'll report to Embark CTO Brandon Moak and focus on boosting the accuracy and distance at which the cameras, radar and laser lidar sensors on its semi-trucks detect other vehicles, as well as leading mapping, localization and machine learning efforts. "Self-driving perception systems need huge amounts of data to train their machine learning algorithms, which means gathering high-quality data is key for Embark's perception team," said CEO Alex Rodrigues.

Daniel Berger, a researcher at MIT, traced these neurons using the EyeWire game. Daniel Berger, a researcher at MIT, traced these neurons using the EyeWire game. People can get pretty addicted to computer games. By some estimates, residents of planet Earth spend 3 billion hours per week playing them. Now some scientists are hoping to make use of all that human capital and harness it for a good cause.