Search

Predicting and understanding how people make decisions has been a long-standing goal in many fields, with quantitative models of human decision-making informing research in both the social sciences and engineering. We show how progress toward this goal can be accelerated by using large datasets to power machine-learning algorithms that are constrained to produce interpretable psychological theories. Conducting the largest experiment on risky choice to date and analyzing the results using gradient-based optimization of differentiable decision theories implemented through artificial neural networks, we were able to recapitulate historical discoveries, establish that there is room to improve on existing theories, and discover a new, more accurate model of human decision-making in a form that preserves the insights from centuries of research., (Copyright © 2021 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works.)

Large-scale behavioral datasets enable researchers to use com-plex machine learning algorithms to better predict human be-havior, yet this increased predictive power does not always leadto a better understanding of the behavior in question. In thispaper, we outline a data-driven, iterative procedure that allowscognitive scientists to use machine learning to generate mod-els that are both interpretable and accurate. We demonstratethis method in the domain of moral decision-making, wherestandard experimental approaches often identify relevant prin-ciples that influence human judgments, but fail to generalizethese findings to “real world” situations that place these prin-ciples in conflict. The recently released Moral Machine datasetallows us to build a powerful model that can predict the out-comes of these conflicts while remaining simple enough to ex-plain the basis behind human decisions.

Do large datasets provide value to psychologists? Without a systematic methodology for working with such datasets, there is a valid concern that analyses will produce noise artifacts rather than true effects. In this paper, we offer a way to enable researchers to systematically build models and identify novel phenomena in large datasets. One traditional approach is to analyze the residuals of models--the biggest errors they make in predicting the data--to discover what might be missing from those models. However, once a dataset is sufficiently large, machine learning algorithms approximate the true underlying function better than the data, suggesting, instead, that the predictions of these data-driven models should be used to guide model building. We call this approach "Scientific Regret Minimization" (SRM), as it focuses on minimizing errors for cases that we know should have been predictable. We apply this exploratory method on a subset of the Moral Machine dataset, a public collection of roughly 40 million moral decisions. Using SRM, we find that incorporating a set of deontological principles that capture dimensions along which groups of agents can vary (e.g., sex and age) improves a computational model of human moral judgment. Furthermore, we are able to identify and independently validate three interesting moral phenomena: criminal dehumanization, age of responsibility, and asymmetric notions of responsibility. [ABSTRACT FROM AUTHOR]

• The white cane is the most common and widely used travel aid for the blind and its cost is not too much and many government hospitals provide for free to needy and poor people. • It's a great tool which helps blind people in detecting uneven surfaces, obstacles on ground, steps, holes and other hazard. • And which may lead to accidents. • The service animals (such as dogs, birds, miniature horses etc.) are good at dealing these types of situations but they are not easy to train and are very expensive. The white cane is the most common and widely used travel aid for the blind. Its cost is not too high and many government hospitals provide it for free to needy and poor people. It is a great tool that helps blind people detect uneven surfaces, obstacles on the ground, steps, holes, and other hazards. However, it has a major drawback in detecting obstacles that are beyond the range of the white cane, especially when the object is in motion. For example, when a blind person crosses the road, they may not be able to detect a car or person coming from either side (left and right), and it is not much help to the user when navigating through crowded places, which can lead to accidents. Service animals (such as dogs, birds, and miniature horses) are good at handling these types of situations, but they are not easy to train and are very expensive. This paper takes references from many papers and proposes a collision detection and prevention system made of integration of many technologies including image processing, cloud computing, machine learning, IoT and audio production devices, with better option for the blind people for navigating through roads and crowded places and using it along with white cane will make it more effective and will be able to cover some drawbacks of the device. [ABSTRACT FROM AUTHOR]