This study presents a theoretical model for a self-replicating mechanical system inspired by biological processes within living cells and supported by computer simulations. The model decomposes self-replication into core components, each of which is executed by a single machine constructed from a set of basic block types. Key functionalities such as sorting, copying, and building, are demonstrated. The model provides valuable insights into the constraints of self-replicating systems. The discussion also addresses the spatial and timing behavior of the system, as well as its efficiency and complexity. This work provides a foundational framework for future studies on self-replicating mechanisms and their information-processing applications.

The topic of comprehensibility of machine-learned theories has recently drawn increasing attention. Inductive Logic Programming (ILP) uses logic programming to derive logic theories from small data based on abduction and induction techniques. Learned theories are represented in the form of rules as declarative descriptions of obtained knowledge. In earlier work, the authors provided the first evidence of a measurable increase in human comprehension based on machine-learned logic rules for simple classification tasks. In a later study, it was found that the presentation of machine-learned explanations to humans can produce both beneficial and harmful effects in the context of game learning. We continue our investigation of comprehensibility by examining the effects of the ordering of concept presentations on human comprehension. In this work, we examine the explanatory effects of curriculum order and the presence of machine-learned explanations for sequential problem-solving. We show that 1) there exist tasks A and B such that learning A before B has a better human comprehension with respect to learning B before A and 2) there exist tasks A and B such that the presence of explanations when learning A contributes to improved human comprehension when subsequently learning B. We propose a framework for the effects of sequential teaching on comprehension based on an existing definition of comprehensibility and provide evidence for support from data collected in human trials. Empirical results show that sequential teaching of concepts with increasing complexity a) has a beneficial effect on human comprehension and b) leads to human re-discovery of divide-and-conquer problem-solving strategies, and c) studying machine-learned explanations allows adaptations of human problem-solving strategy with better performance.

On July 14, Key Technology debuted its new FM Alert software driven by artificial intelligence (AI). The new AI alert system can help processors control foreign materials entering product streams, as well as improving documentation and overall food safety. It will be a part of the company's exhibit at Pack Expo in October at booth S-3547. The AI system captures and saves images of foreign materials (FMs) that a sorter detects and rejects from its stream, with data available immediately to alert operators. "Thanks to the application of advanced artificial intelligence, our new FM Alert software achieves uniquely accurate results -- identifying, recording and acting on true FM findings on the line," said Marco Azzaretti, director of marketing at Key. "The food processing industry continues to focus more and more on elevating food safety. By making product safer, this effective FM-fighting tool helps customers protect their brand's reputation and avoid costly recalls. Every food processor wants to prevent contamination, making FM Alert universally beneficial across all applications."

Key Technology introduces AI-driven FM alert software for its digital sorting systems. This powerful tool captures and saves digital images of critical foreign material (FM) contaminants that the sorter detects and rejects from the product stream. Data outputs from the software can be utilized to immediately alert operators and/or signal a downstream device. AI-enhanced FM Alert helps processors better control FM and improve documentation to protect food safety. "Thanks to the application of advanced artificial intelligence, our new FM Alert software achieves uniquely accurate results – identifying, recording, and acting on true FM findings on the line," said Marco Azzaretti, director of marketing at Key. "The food processing industry continues to focus more and more on elevating food safety. By making product safer, this effective FM-fighting tool helps customers protect their brand's reputation and avoid costly recalls. Every food processor wants to prevent contamination, making FM Alert universally beneficial across all applications."

Editor's note: This is part of a series about ongoing risks and evolving labor issues in the recycling industry. Read more about persistent safety hazards and how MRF operators are responding. Also check out a feature on the firsthand experiences of California workers and the complex medical claim process they face. In MRFs across the U.S., dozens of arms hover over conveyors and appear to be in nearly constant motion sorting incoming materials. Previously, those arms exclusively were attached to humans. Now, a shift is occurring. Increasingly, more of those are arms attached to robots that use pincers or suction cups, instead of fingers, and move much faster. Advanced MRF automation and robotics weren't widely adopted concepts up until about five years ago, according to equipment manufacturers.

For some people, rummaging through a bunch of Lego bricks is part of the fun. But if you've got an enormous collection or take on complicated builds, you probably have a system for sorting your pieces. Your solution probably doesn't involve AI, though. YouTube user Daniel West combined his love for Lego with his engineering skills to build a universal Lego sorter that uses a neural network to identify, classify and organize the plastic pieces more efficiently than a human could. The universal Lego sorter -- which is made up of 10,000 Lego bricks -- took two years to design, build and perfect.

During the 2017 project pilot phase, the Carton Council provided MRFs with grants to purchase and work with AMP to install carton-sorting robots. The first was at Alpine Waste & Recycling in Colorado, followed soon after by one at Dem-Con Companies in Minnesota. Past the pilot phase, the robots are now ready for prime time and there have been growing numbers of installations in the U.S. and Canada. This summer, another carton-sorting robot was installed at Single Stream Recyclers in Sarasota, Florida, along with several robots to sort other valuable materials and help to reduce contamination. With arms and grippers that can pick materials out of the recycling stream faster and with a higher rate of accuracy than their human counterparts, these robots utilize a vision centre with a camera that allows for monitoring materials as they pass through on a conveyer belt.

Every year trash companies sift through an estimated 68 million tons of recycling, which is the weight equivalent of more than 30 million cars. A key step in the process happens on fast-moving conveyor belts, where workers have to sort items into categories like paper, plastic and glass. Such jobs are dull, dirty, and often unsafe, especially in facilities where workers also have to remove normal trash from the mix. With that in mind, a team led by researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed a robotic system that can detect if an object is paper, metal, or plastic. The team's "RoCycle" system includes a soft Teflon hand that uses tactile sensors on its fingertips to detect an object's size and stiffness.

Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Surrogate and relaxation methods exist but tend to be specific to a given metric. In the present work, we introduce a new method to learn approximations of such non-differentiable objective functions. Our approach is based on a deep architecture that approximates the sorting of arbitrary sets of scores. It is trained virtually for free using synthetic data. This sorting deep (SoDeep) net can then be combined in a plug-and-play manner with existing deep architectures. We demonstrate the interest of our approach in three different tasks that require ranking: Cross-modal text-image retrieval, multi-label image classification and visual memorability ranking. Our approach yields very competitive results on these three tasks, which validates the merit and the flexibility of SoDeep as a proxy for sorting operation in ranking-based losses.

Jacques Mattheij didn't expect to buy two tons of Lego bricks. But that's what happened after an evening of bidding -- or rather, overbidding -- on bulk lots of used bricks on eBay. His plan was to resell the bricks at a profit. But he won more than expected, and by morning, he owned more than 2 million pieces. Now he needed to sort them to get the best price.