Mapping the knowledge domain of soft computing applications for emergency evacuation studies: A scientometric analysis and critical review

Engineering BPQDs/PLGA nanospheres-Integrated Wood Hydrogel Bionic Scaffold for Combinatory Bone Repair and Osteolytic Tumor Therapy

Nest-like nanofiber structures have potential applications in surface modifications of titanium implants. In this study, nest-like nanofiber structures were prepared on a titanium surface at room temperature and pressure by using the nanobowl template-assisted method combined with alkali etching. The characterization and biocompatibility of this material were analyzed by cellular adhesion, death, CCK-8, ALP, and RT-PCR assays in vitro, and osseointegration was evaluated by micro-CT and fluorescent labeling in vivo. The results showed that this nest-like nanofiber structure has a firmer and asperate surface than nanotubes, which leads to better cellular adhesion, proliferation, and differentiation capacity. In a beagle alveolar bone implant model, the nest-like nanofiber structure showed a better osseointegration capacity. In conclusion, this nest-like nanofiber structure has potential applications in dental implantology.

/pdf/titanium-nanobowl-based-nest-like-nanofiber-structure-7r8ol6yk.pdf

Titanium Nanobowl-Based Nest-Like Nanofiber Structure Prepared at Room Temperature and Pressure Promotes Osseointegration of Beagle Implants

Internet of Vehicles (IoV) technology has been attracting great interest from both academia and industry due to its huge potential impact on improving driving experiences and enabling better transportation systems. While a large number of interesting IoV applications are expected, it is more challenging to design an efficient IoV system compared with conventional Internet of Things (IoT) applications due to the mobility of vehicles and complex road conditions. We discuss existing studies about enabling collaborative intelligence in IoV systems by focusing on collaborative communications, collaborative computing, and collaborative machine learning approaches. Based on comparison and discussion about the advantages and disadvantages of recent studies, we point out open research issues and future research directions.

/pdf/toward-collaborative-intelligence-in-iov-systems-recent-16tgetqg.pdf

Toward Collaborative Intelligence in IoV Systems: Recent Advances and Open Issues

We are at the cusp of a transition from ‘learning from data’ to ‘learning what data to learn from’ as a central focus of artificial intelligence (AI) research. While the first-order learning problem is not completely solved, large models under unified architectures, such as transformers, have shifted the learning bottleneck from how to effectively train models to how to effectively acquire and use task-relevant data. This problem, which we frame as exploration, is a universal aspect of learning in open-ended domains like the real world. Although the study of exploration in AI is largely limited to the field of reinforcement learning, we argue that exploration is essential to all learning systems, including supervised learning. We propose the problem of generalized exploration to conceptually unify exploration-driven learning between supervised learning and reinforcement learning, allowing us to highlight key similarities across learning settings and open research challenges. Importantly, generalized exploration is a necessary objective for maintaining open-ended learning processes, which in continually learning to discover and solve new problems, provides a promising path to more general intelligence.

General intelligence requires rethinking exploration

In the past decade, we have witnessed the rise of deep learning to dominate the field of artificial intelligence. Advances in artificial neural networks alongside corresponding advances in hardware accelerators with large memory capacity, together with the availability of large datasets enabled practitioners to train and deploy sophisticated neural network models that achieve state-of-the-art performance on tasks across several fields spanning computer vision, natural language processing, and reinforcement learning. However, as these neural networks become bigger, more complex, and more widely used, fundamental problems with current deep learning models become more apparent. State-of-the-art deep learning models are known to suffer from issues that range from poor robustness, inability to adapt to novel task settings, to requiring rigid and inflexible configuration assumptions. Collective behavior, commonly observed in nature, tends to produce systems that are robust, adaptable, and have less rigid assumptions about the environment configuration. Collective intelligence, as a field, studies the group intelligence that emerges from the interactions of many individuals. Within this field, ideas such as self-organization, emergent behavior, swarm optimization, and cellular automata were developed to model and explain complex systems. It is therefore natural to see these ideas incorporated into newer deep learning methods. In this review, we will provide a historical context of neural network research’s involvement with complex systems, and highlight several active areas in modern deep learning research that incorporate the principles of collective intelligence to advance its capabilities. We hope this review can serve as a bridge between the complex systems and deep learning communities. 

/pdf/collective-intelligence-for-deep-learning-a-survey-of-recent-17xdhy8x.pdf

Stanley Devine

Papers

Collective intelligence for deep learning: A survey of recent developments

Carfilzomib alleviated osteoporosis by targeting PSME1/2 to activate Wnt/β-catenin signaling.

Carfilzomib alleviated osteoporosis by targeting PSME1/2 to activate Wnt/β-catenin signaling