In the field of machine learning, the well-trained model is assumed to be able to recover the training labels, i.e. the synthetic labels predicted by the model should be as close to the ground-truth labels as possible. Inspired by this, we propose a self-guided curriculum strategy to encourage the learning of neural machine translation (NMT) models to follow the above recovery criterion, where we cast the recovery degree of each training example as its learning difficulty. Specifically, we adopt the sentence level BLEU score as the proxy of recovery degree. Different from existing curricula relying on linguistic prior knowledge or third-party language models, our chosen learning difficulty is more suitable to measure the degree of knowledge mastery of the NMT models. Experiments on translation benchmarks, including WMT14 English$\Rightarrow$German and WMT17 Chinese$\Rightarrow$English, demonstrate that our approach can consistently improve translation performance against strong baseline Transformer.

This paper presents a framework that allows online dynamic-stability-constrained optimal trajectory planning of a mobile manipulator robot working on rough terrain. First, the kinematics model of a mobile manipulator robot, and the Zero Moment Point (ZMP) stability measure are presented as theoretical background. Then, a sampling-based quasi-static planning algorithm modified for stability guarantee and traction optimization in continuous dynamic motion is presented along with a mathematical proof. The robot's quasi-static path is then used as an initial guess to warm-start a nonlinear optimal control solver which may otherwise have difficulties finding a solution to the stability-constrained formulation efficiently. The performance and computational efficiency of the framework are demonstrated through an application to a simulated timber harvesting mobile manipulator machine working on varying terrain. The results demonstrate feasibility of online trajectory planning on varying terrain while satisfying the dynamic stability constraint.

Biomimetic soft camouflaging skins can one day be used to replicate the color-changing functions of living organisms' skins and aid in achieving active camouflage and paving the way for revolutionary changes in robotics. An international team of scientists From China and Germany has taken a step toward that goal -- all the while establishing a novel technology that can detect seafood freshness. Scientists created an artificial color-changing material that mimics chameleon skin by organizing luminogens (molecules that make crystals glow) into various core and shell hydrogel layers rather than one uniform matrix, according to a study published in the journal Cell Reports Physical Science. Thanks to this new design, a two-luminogen hydrogel chemosensor can be used to detect seafood freshness by changing color according to the amine -- an organic compound formed by replacing one or more hydrogen atoms in ammonia with organic groups -- vapors emitted by microbes as fish goes bad. This concept goes back a couple of decades since scientists have already envisioned developing soft materials that can change color with ease.

An artificial colour-changing material inspired by the skins of chameleons can be used as a chemical sensor to determine whether seafood is fresh, a study found. Developed by experts from China, the device switches from pink to green in the presence of the amine vapours released by microbes when fish and shrimp spoil. The novel material could also find applications in the development of anticounterfeit technology, camouflage for robots and stretchable electronics, the team said. Panther chameleons are colour-changing reptiles native to the island of Madagascar in the Indian Ocean. Males of the species -- which are more brightly coloured than their female counterparts and change hue when asserting their dominance -- can grow to around 8 inches (20 cm) in length.

The quantification of positively buoyant marine plastic debris is critical to understanding how concentrations of trash from across the world's ocean and identifying high concentration garbage hotspots in dire need of trash removal. Currently, the most common monitoring method to quantify floating plastic requires the use of a manta trawl. Techniques requiring manta trawls (or similar surface collection devices) utilize physical removal of marine plastic debris as the first step and then analyze collected samples as a second step. The need for physical removal before analysis incurs high costs and requires intensive labor preventing scalable deployment of a real-time marine plastic monitoring service across the entirety of Earth's ocean bodies. Without better monitoring and sampling methods, the total impact of plastic pollution on the environment as a whole, and details of impact within specific oceanic regions, will remain unknown. This study presents a highly scalable workflow that utilizes images captured within the epipelagic layer of the ocean as an input. It produces real-time quantification of marine plastic debris for accurate quantification and physical removal. The workflow includes creating and preprocessing a domain-specific dataset, building an object detection model utilizing a deep neural network, and evaluating the model's performance. YOLOv5-S was the best performing model, which operates at a Mean Average Precision (mAP) of 0.851 and an F1-Score of 0.89 while maintaining near-real-time speed.

The human voice conveys unique characteristics of an individual, making voice biometrics a key technology for verifying identities in various industries. Despite the impressive progress of speaker recognition systems in terms of accuracy, a number of ethical and legal concerns has been raised, specifically relating to the fairness of such systems. In this paper, we aim to explore the disparity in performance achieved by state-of-the-art deep speaker recognition systems, when different groups of individuals characterized by a common sensitive attribute (e.g., gender) are considered. In order to mitigate the unfairness we uncovered by means of an exploratory study, we investigate whether balancing the representation of the different groups of individuals in the training set can lead to a more equal treatment of these demographic groups. Experiments on two state-of-the-art neural architectures and a large-scale public dataset show that models trained with demographically-balanced training sets exhibit a fairer behavior on different groups, while still being accurate. Our study is expected to provide a solid basis for instilling beyond-accuracy objectives (e.g., fairness) in speaker recognition.

Steel pipes are widely used in high-risk and high-pressure scenarios such as oil, chemical, natural gas, shale gas, etc. If there is some defect in steel pipes, it will lead to serious adverse consequences. Applying object detection in the field of deep learning to pipe weld defect detection and identification can effectively improve inspection efficiency and promote the development of industrial automation. Most predecessors used traditional computer vision methods applied to detect defects of steel pipe weld seams. However, traditional computer vision methods rely on prior knowledge and can only detect defects with a single feature, so it is difficult to complete the task of multi-defect classification, while deep learning is end-to-end. In this paper, the state-of-the-art single-stage object detection algorithm YOLOv5 is proposed to be applied to the field of steel pipe weld defect detection, and compared with the two-stage representative object detection algorithm Faster R-CNN. The experimental results show that applying YOLOv5 to steel pipe weld defect detection can greatly improve the accuracy, complete the multi-classification task, and meet the criteria of real-time detection.

Concepts similar to emergence have been used since antiquity, but we lack an agreed definition of emergence. Still, emergence has been identified as one of the features of complex systems. Most would agree on the statement "life is complex". Thus, understanding emergence and complexity should benefit the study of living systems. It can be said that life emerges from the interactions of complex molecules. But how useful is this to understand living systems? Artificial life (ALife) has been developed in recent decades to study life using a synthetic approach: build it to understand it. ALife systems are not so complex, be them soft (simulations), hard (robots), or wet (protocells). Then, we can aim at first understanding emergence in ALife, for then using this knowledge in biology. I argue that to understand emergence and life, it becomes useful to use information as a framework. In a general sense, emergence can be defined as information that is not present at one scale but is present at another scale. This perspective avoids problems of studying emergence from a materialistic framework, and can be useful to study self-organization and complexity.

In today's world, technology leads business and these are not just any tech but specifically AI and other disruptive systems. We have witnessed how the pandemic accelerated the rapid growth and adoption of these cutting-edge technologies. According to Reportlinker research, the global AI market is projected to grow by USD 76.44 billion during 2021-2025, at a CAGR of 21%. Artificial intelligence has revolutionized businesses and industries by introducing automation and intelligent business operations. Many giant firms are leading the AI race and competing consistently to enhance their markets.

In a sunny field in Hampshire, a killer robot is on the prowl. Once its artificial intelligence engine has locked on to its target, a black electrode descends and delivers an 8,000-volt blast. A crackle, a puff of smoke, and the target is dead – a weed, boiled alive from the inside. It is part of a fourth agricultural revolution, its makers say, bringing automation and big data into farming to produce more while harming the environment less. Pressure to cut pesticide use and increasing resistance to the chemicals meant killing weeds was the top priority for the farmers advising the robot company.