Humans and other intelligent agents often rely on collective decision making based on an intuition that groups outperform individuals. However, at present, we lack a complete theoretical understanding of when groups perform better. Here we examine performance in collective decision-making in the context of a real-world citizen science task environment in which individuals with manipulated differences in task-relevant training collaborated. We find 1) dyads gradually improve in performance but do not experience a collective benefit compared to individuals in most situations; 2) the cost of coordination to efficiency and speed that results when switching to a dyadic context after training individually is consistently larger than the leverage of having a partner, even if they are expertly trained in that task; and 3) on the most complex tasks having an additional expert in the dyad who is adequately trained improves accuracy. These findings highlight that the extent of training received by an individual, the complexity of the task at hand, and the desired performance indicator are all critical factors that need to be accounted for when weighing up the benefits of collective decision-making.
相關內容
Most continual learning (CL) algorithms have focused on tackling the stability-plasticity dilemma, that is, the challenge of preventing the forgetting of previous tasks while learning new ones. However, they have overlooked the impact of the knowledge transfer when the dataset in a certain task is biased - namely, when some unintended spurious correlations of the tasks are learned from the biased dataset. In that case, how would they affect learning future tasks or the knowledge already learned from the past tasks? In this work, we carefully design systematic experiments using one synthetic and two real-world datasets to answer the question from our empirical findings. Specifically, we first show through two-task CL experiments that standard CL methods, which are unaware of dataset bias, can transfer biases from one task to another, both forward and backward, and this transfer is exacerbated depending on whether the CL methods focus on the stability or the plasticity. We then present that the bias transfer also exists and even accumulate in longer sequences of tasks. Finally, we propose a simple, yet strong plug-in method for debiasing-aware continual learning, dubbed as Group-class Balanced Greedy Sampling (BGS). As a result, we show that our BGS can always reduce the bias of a CL model, with a slight loss of CL performance at most.
Despite the promising results achieved, state-of-the-art interactive reinforcement learning schemes rely on passively receiving supervision signals from advisor experts, in the form of either continuous monitoring or pre-defined rules, which inevitably result in a cumbersome and expensive learning process. In this paper, we introduce a novel initiative advisor-in-the-loop actor-critic framework, termed as Ask-AC, that replaces the unilateral advisor-guidance mechanism with a bidirectional learner-initiative one, and thereby enables a customized and efficacious message exchange between learner and advisor. At the heart of Ask-AC are two complementary components, namely action requester and adaptive state selector, that can be readily incorporated into various discrete actor-critic architectures. The former component allows the agent to initiatively seek advisor intervention in the presence of uncertain states, while the latter identifies the unstable states potentially missed by the former especially when environment changes, and then learns to promote the ask action on such states. Experimental results on both stationary and non-stationary environments and across different actor-critic backbones demonstrate that the proposed framework significantly improves the learning efficiency of the agent, and achieves the performances on par with those obtained by continuous advisor monitoring.
Existing research on merging behavior generally prioritize the application of various algorithms, but often overlooks the fine-grained process and analysis of trajectories. This leads to the neglect of surrounding vehicle matching, the opaqueness of indicators definition, and reproducible crisis. To address these gaps, this paper presents a reproducible approach to merging behavior analysis. Specifically, we outline the causes of subjectivity and irreproducibility in existing studies. Thereafter, we employ lanelet2 High Definition (HD) map to construct a reproducible framework, that minimizes subjectivities, defines standardized indicators, identifies alongside vehicles, and divides scenarios. A comparative macroscopic and microscopic analysis is subsequently conducted. More importantly, this paper adheres to the Reproducible Research concept, providing all the source codes and reproduction instructions. Our results demonstrate that although scenarios with alongside vehicles occur in less than 6% of cases, their characteristics are significantly different from others, and these scenarios are often accompanied by high risk. This paper refines the understanding of merging behavior, raises awareness of reproducible studies, and serves as a watershed moment.
Recent advancements in decision-making large language model (LLM) agents have demonstrated impressive performance across various benchmarks. However, these state-of-the-art approaches typically necessitate internal model fine-tuning, external model fine-tuning, or policy optimization over a defined state space. Implementing these methods can prove challenging due to the scarcity of high-quality training data or the lack of well-defined state space. Moreover, these agents do not possess certain qualities inherent to human decision-making processes, specifically the ability to learn from mistakes. Self-reflection allows humans to efficiently solve novel problems through a process of trial and error. Building on recent research, we propose Reflexion, an approach that endows an agent with dynamic memory and self-reflection capabilities to enhance its existing reasoning trace and task-specific action choice abilities. To achieve full automation, we introduce a straightforward yet effective heuristic that enables the agent to pinpoint hallucination instances, avoid repetition in action sequences, and, in some environments, construct an internal memory map of the given environment. To assess our approach, we evaluate the agent's ability to complete decision-making tasks in AlfWorld environments and knowledge-intensive, search-based question-and-answer tasks in HotPotQA environments. We observe success rates of 97% and 51%, respectively, and provide a discussion on the emergent property of self-reflection.
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.
Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely implausible: they require (1) extraordinarily large amounts of data, (2) unobtainable supervised labels, (3) textual rather than raw sensory input, and / or (4) implausibly large memory (e.g. thousands of contextual words). These elements highlight the need to identify algorithms that, under these limitations, would suffice to account for both behavioral and brain responses. Focusing on the issue of speech processing, we here hypothesize that self-supervised algorithms trained on the raw waveform constitute a promising candidate. Specifically, we compare a recent self-supervised architecture, Wav2Vec 2.0, to the brain activity of 412 English, French, and Mandarin individuals recorded with functional Magnetic Resonance Imaging (fMRI), while they listened to ~1h of audio books. Our results are four-fold. First, we show that this algorithm learns brain-like representations with as little as 600 hours of unlabelled speech -- a quantity comparable to what infants can be exposed to during language acquisition. Second, its functional hierarchy aligns with the cortical hierarchy of speech processing. Third, different training regimes reveal a functional specialization akin to the cortex: Wav2Vec 2.0 learns sound-generic, speech-specific and language-specific representations similar to those of the prefrontal and temporal cortices. Fourth, we confirm the similarity of this specialization with the behavior of 386 additional participants. These elements, resulting from the largest neuroimaging benchmark to date, show how self-supervised learning can account for a rich organization of speech processing in the brain, and thus delineate a path to identify the laws of language acquisition which shape the human brain.
Future astronauts living and working on the Moon will face extreme environmental conditions impeding their operational safety and performance. While it has been suggested that Augmented Reality (AR) Head-Up Displays (HUDs) could potentially help mitigate some of these adversities, the applicability of AR in the unique lunar context remains underexplored. To address this limitation, we have produced an accurate representation of the lunar setting in virtual reality (VR) which then formed our testbed for the exploration of prospective operational scenarios with aerospace experts. Herein we present findings based on qualitative reflections made by the first 6 study participants. AR was found instrumental in several use cases, including the support of navigation and risk awareness. Major design challenges were likewise identified, including the importance of redundancy and contextual appropriateness. Drawing on these findings, we conclude by outlining directions for future research aimed at developing AR-based assistive solutions tailored to the lunar setting.
New emerging technologies powered by Artificial Intelligence (AI) have the potential to disruptively transform our societies for the better. In particular, data-driven learning approaches (i.e., Machine Learning (ML)) have been a true revolution in the advancement of multiple technologies in various application domains. But at the same time there is growing concern about certain intrinsic characteristics of these methodologies that carry potential risks to both safety and fundamental rights. Although there are mechanisms in the adoption process to minimize these risks (e.g., safety regulations), these do not exclude the possibility of harm occurring, and if this happens, victims should be able to seek compensation. Liability regimes will therefore play a key role in ensuring basic protection for victims using or interacting with these systems. However, the same characteristics that make AI systems inherently risky, such as lack of causality, opacity, unpredictability or their self and continuous learning capabilities, may lead to considerable difficulties when it comes to proving causation. This paper presents three case studies, as well as the methodology to reach them, that illustrate these difficulties. Specifically, we address the cases of cleaning robots, delivery drones and robots in education. The outcome of the proposed analysis suggests the need to revise liability regimes to alleviate the burden of proof on victims in cases involving AI technologies.
With the rise of AI and data mining techniques, group profiling and group-level analysis have been increasingly used in many domains including policy making and direct marketing. In some cases, the statistics extracted from data may provide insights to a group's shared characteristics; in others, the group-level analysis can lead to problems including stereotyping and systematic oppression. How can analytic tools facilitate a more conscientious process in group analysis? In this work, we identify a set of accountable group analytics design guidelines to explicate the needs for group differentiation and preventing overgeneralization of a group. Following the design guidelines, we develop TribalGram, a visual analytic suite that leverages interpretable machine learning algorithms and visualization to offer inference assessment, model explanation, data corroboration, and sense-making. Through the interviews with domain experts, we showcase how our design and tools can bring a richer understanding of "groups" mined from the data.
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191