Navigation is one of the most heavily studied problems in robotics and is conventionally approached as a geometric mapping and planning problem. However, real-world navigation presents a complex set of physical challenges that defies simple geometric abstractions. Machine learning offers a promising way to go beyond geometry and conventional planning, allowing for navigational systems that make decisions based on actual prior experience. Such systems can reason about traversability in ways that go beyond geometry, accounting for the physical outcomes of their actions and exploiting patterns in real-world environments. They can also improve as more data is collected, potentially providing a powerful network effect. In this article, we present a general toolkit for experiential learning of robotic navigation skills that unifies several recent approaches, describe the underlying design principles, summarize experimental results from several of our recent papers, and discuss open problems and directions for future work.
This article is part of the theme issue ‘New approaches to 3D vision’.
Digital pathology is a technology that allows pathological information created from a digital slide to be accessed, handled, and interpreted. Using optical pathology scanners, glass slides are collected and transformed to digitized glass slides that can be viewed on your computer monitor. Relevant support for education and the practice of human anatomy is offered by digital pathology. With the recent developments in digital pathology led to computer-aided diagnosis using machine learning approaches. So, machine learning frameworks assist physicians in diagnosing critical cases such as cancer, tumors, etc and improve patient management. With an ever growing number of choices, it can be hard to pick a better machine learning method for pathological data. Big potential attempts are made in this paper to research the full context of digital pathology with the specifics of how artificial intelligence has contributed to digital pathology. This review also analyzes various machine learning frameworks by providing as much information as possible and quantifying what the tradeoffs will be. This paper ultimately provides the improvements in the frameworks available that will be required in the near future applications.
Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by this seminal finding, in this study we propose a creative decoder within a deep generative framework, which involves direct modulation of the neuronal activation pattern after sampling from the learned latent space. The proposed approach is fully unsupervised and can be used off- the-shelf. Several novelty metrics and human evaluation were used to evaluate the creative capacity of the deep decoder. Our experiments on different image datasets (MNIST, FMNIST, MNIST+FMNIST, WikiArt and CelebA) reveal that atypical co-activation of highly activated and weakly activated neurons in a deep decoder promotes generation of novel and meaningful artifacts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.