Trust is the foundation of every area of life. Without it, it is difficult to build lasting relationships. Unfortunately, in recent years, trust has been severely damaged by the spread of fake news and disinformation, which has become a serious social problem. In addition to trust, the factor influencing interpersonal relationships is perceived attractiveness, which is currently created to a large extent by digital media. Understanding the principles of judging others can be helpful in fighting prejudice and rebuilding trust in society. One way to learn about people's choices is to record their brain activity as they make choices. The article presents an experiment in which the faces of different people were presented, and the participants' task was to assess how much they can trust a given person and how attractive they are. During the study, the EEG signal was recorded, which was used to build models of logistic regression classifiers. In addition, the most active areas of the brain that participate in the assessment of trust and attractiveness of the face were indicated.
相關內容
Identifying subgroups of patients who benefit from a treatment is a key aspect of personalized medicine, these subgroups can be used to develop individualized treatment rules (ITRs). Many machine learning methods have been proposed to create such rules. However, to what extent methods lead to the same ITRs, i.e., recommending the same treatment for the same individuals is unclear. To see if methods lead to similar ITRs, we compared the most common approaches in two randomized control trials. Two classes of methods can be distinguished to develop an ITR. The first class of methods relies on predicting individualized treatment effects from which an ITR is derived by recommending the evaluated treatment to the individuals with a predicted benefit. In the second class, methods directly estimate the ITR without estimating individualized treatment effects. For each trial, the performance of ITRs was assessed with various metrics, and the pairwise agreement between ITRs was also calculated. Results showed that the ITRs obtained by the different methods generally had considerable disagreements regarding the individuals to be treated. A better concordance was found among akin methods. Overall, when evaluating the performance of ITRs in a validation sample, all methods produced ITRs with limited performance, suggesting a high potential for overfitting. The different methods do not lead to similar ITRs and are therefore not interchangeable. The choice of the method has a lot of influence on which patients end up being given a certain treatment which draws some concerns about the practical use of the methods.
Aiming for a mixbiotic society that combines freedom and solidarity among people with diverse values, I focused on nonviolent communication (NVC) that enables compassionate giving in various situations of social division and conflict, and tried a generative AI for it. Specifically, ChatGPT was used in place of the traditional certified trainer to test the possibility of mediating (modifying) input sentences in four processes: observation, feelings, needs, and requests. The results indicate that there is potential for the application of generative AI, although not yet at a practical level. Suggested improvement guidelines included adding model responses, relearning revised responses, specifying appropriate terminology for each process, and re-asking for required information. The use of generative AI will be useful initially to assist certified trainers, to prepare for and review events and workshops, and in the future to support consensus building and cooperative behavior in digital democracy, platform cooperatives, and cyber-human social co-operating systems. It is hoped that the widespread use of NVC mediation using generative AI will lead to the early realization of a mixbiotic society.
Groups coordinate more effectively when individuals are able to learn from others' successes. But acquiring such knowledge is not always easy, especially in real-world environments where success is hidden from public view. We suggest that social inference capacities may help bridge this gap, allowing individuals to update their beliefs about others' underlying knowledge and success from observable trajectories of behavior. We compared our social inference model against simpler heuristics in three studies of human behavior in a collective sensing task. In Experiment 1, we found that average performance improves as a function of group size at a rate greater than predicted by non-inferential models. Experiment 2 introduced artificial agents to evaluate how individuals selectively rely on social information. Experiment 3 generalized these findings to a more complex reward landscape. Taken together, our findings provide insight into the relationship between individual social cognition and the flexibility of collective behavior.
As advancements in artificial intelligence (AI) propel progress in the life sciences, they may also enable the weaponisation and misuse of biological agents. This article differentiates two classes of AI tools that pose such biosecurity risks: large language models (LLMs) and biological design tools (BDTs). LLMs, such as GPT-4, are already able to provide dual-use information that removes some barriers encountered by historical biological weapons efforts. As LLMs are turned into lab assistants and autonomous science tools, this will further increase their ability to support research. Thus, LLMs will in particular lower barriers to biological misuse. In contrast, BDTs will expand the capabilities of sophisticated actors. Concretely, BDTs may enable the creation of pandemic pathogens substantially worse than anything seen to date and could enable forms of more predictable and targeted biological weapons. In combination, LLMs and BDTs could raise the ceiling of harm from biological agents and could make them broadly accessible. A range of interventions would help to manage risks. Independent pre-release evaluations could ensure that developers have eliminated dangerous capabilities of new models. Risks from powerful science tools might be mitigated through providing differentiated access to legitimate researchers. Lastly, essential for mitigating risks will be universal and enhanced screening of gene synthesis products.
We present our proposed solution to the BabyLM challenge [arXiv:2301.11796], whose goal was to improve the sample efficiency of language models. We trained an ensemble consisting of a GPT-2 and small LLaMA models on the developmentally-plausible, 10M-word BabyLM dataset, then distilled it into a small, 58M-parameter LLaMA model, which exceeds in performance both of its teachers as well as a similar model trained without distillation. This suggests that distillation can not only retain the full performance of the teacher model when the latter is trained on a sufficiently small dataset; it can exceed it, and lead to significantly better performance than direct training.
The Laplace approximation is a popular method for providing posterior mean and variance estimates. But can we trust these estimates for practical use? One might consider using rate-of-convergence bounds for the Bayesian Central Limit Theorem (BCLT) to provide quality guarantees for the Laplace approximation. But the bounds in existing versions of the BCLT either: require knowing the true data-generating parameter, are asymptotic in the number of samples, do not control the Bayesian posterior mean, or apply only to narrow classes of models. Our work provides the first closed-form, finite-sample quality bounds for the Laplace approximation that simultaneously (1) do not require knowing the true parameter, (2) control posterior means and variances, and (3) apply generally to models that satisfy the conditions of the asymptotic BCLT. In fact, our bounds work even in the presence of misspecification. We compute exact constants in our bounds for a variety of standard models, including logistic regression, and numerically demonstrate their utility. We provide a framework for analysis of more complex models.
In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past examples, enabling relational gradients for the student. We then show that the normalisation of representations is tightly coupled with the training dynamics of this projector, which can have a large impact on the students performance. Finally, we show that a simple soft maximum function can be used to address any significant capacity gap problems. Experimental results on various benchmark datasets demonstrate that using these insights can lead to superior or comparable performance to state-of-the-art knowledge distillation techniques, despite being much more computationally efficient. In particular, we obtain these results across image classification (CIFAR100 and ImageNet), object detection (COCO2017), and on more difficult distillation objectives, such as training data efficient transformers, whereby we attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet.
Accurate predictions, as with machine learning, may not suffice to provide optimal healthcare for every patient. Indeed, prediction can be driven by shortcuts in the data, such as racial biases. Causal thinking is needed for data-driven decisions. Here, we give an introduction to the key elements, focusing on routinely-collected data, electronic health records (EHRs) and claims data. Using such data to assess the value of an intervention requires care: temporal dependencies and existing practices easily confound the causal effect. We present a step-by-step framework to help build valid decision making from real-life patient records by emulating a randomized trial before individualizing decisions, eg with machine learning. Our framework highlights the most important pitfalls and considerations in analysing EHRs or claims data to draw causal conclusions. We illustrate the various choices in studying the effect of albumin on sepsis mortality in the Medical Information Mart for Intensive Care database (MIMIC-IV). We study the impact of various choices at every step, from feature extraction to causal-estimator selection. In a tutorial spirit, the code and the data are openly available.
This paper does not describe a working system. Instead, it presents a single idea about representation which allows advances made by several different groups to be combined into an imaginary system called GLOM. The advances include transformers, neural fields, contrastive representation learning, distillation and capsules. GLOM answers the question: How can a neural network with a fixed architecture parse an image into a part-whole hierarchy which has a different structure for each image? The idea is simply to use islands of identical vectors to represent the nodes in the parse tree. If GLOM can be made to work, it should significantly improve the interpretability of the representations produced by transformer-like systems when applied to vision or language
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191