Chain of thought prompting successfully improves the reasoning capabilities of large language models, achieving state of the art results on a range of datasets. However, these reasoning capabilities only appear to emerge in models with a size of over 100 billion parameters. In this paper, we explore the transfer of such reasoning capabilities to models with less than 100 billion parameters via knowledge distillation. Specifically, we finetune a student model on the chain of thought outputs generated by a larger teacher model. Our experiments show that the proposed method improves task performance across arithmetic, commonsense and symbolic reasoning datasets. For example, the accuracy of T5 XXL on GSM8K improves from 8.11% to 21.99% when finetuned on PaLM-540B generated chains of thought.

图神经网络（GNN）在各种与图形相关的任务上非常有效。但是，它们缺乏解释性和透明度。当前的解释性方法通常是局部的，将GNN视为黑盒。他们不在模型内部看，抑制了人类对模型和解释的信任。由神经元在视觉模型中检测高级语义概念的能力的动机，我们对单个GNN神经元的行为回答有关GNN可解释性的问题进行了新的分析，并提出了新的指标来评估GNN神经元的可解释性。我们提出了一种新颖的方法，用于使用神经元级概念为GNN产生全球解释，以使从业者能够对模型具有高级的看法。具体而言，（i）据我们所知，这是第一部作品，表明GNN神经元充当概念探测器，并且与表述为节点学位和邻居属性的逻辑组成的概念具有很强的一致性； （ii）我们定量评估检测概念的重要性，并确定训练持续时间和神经元水平的解释性之间的权衡； （iii）我们证明，我们的全球解释性方法比当前的最新方法具有优势 - 我们可以将解释解释为以逻辑描述为支持的单个可解释概念，从而降低了偏见的潜力并提高用户友好性。

图形神经网络的不透明推理导致缺乏人类的信任。现有的图形网络解释器试图通过提供事后解释来解决此问题，但是，它们无法使模型本身更容易解释。为了填补这一空白，我们介绍了概念编码器模块，这是图形网络的第一个可区分概念 - 发现方法。所提出的方法使图形网络可以通过首先发现图形概念，然后使用这些来解决任务来解释。我们的结果表明，这种方法允许图形网络：（i）达到模型准确性与它们的等效香草版本相当，（ii）发现有意义的概念，以实现高概念完整性和纯度得分，（iii）提供基于高质量的概念逻辑。对其预测的解释，以及（iv）在测试时支持有效的干预措施：这些可以提高人类的信任并显着提高模型绩效。

We study the multiclass classification problem where the features come from the mixture of time-homogeneous diffusions. Specifically, the classes are discriminated by their drift functions while the diffusion coefficient is common to all classes and unknown. In this framework, we build a plug-in classifier which relies on nonparametric estimators of the drift and diffusion functions. We first establish the consistency of our classification procedure under mild assumptions and then provide rates of cnvergence under different set of assumptions. Finally, a numerical study supports our theoretical findings.

In recent years, we have seen a significant interest in data-driven deep learning approaches for video anomaly detection, where an algorithm must determine if specific frames of a video contain abnormal behaviors. However, video anomaly detection is particularly context-specific, and the availability of representative datasets heavily limits real-world accuracy. Additionally, the metrics currently reported by most state-of-the-art methods often do not reflect how well the model will perform in real-world scenarios. In this article, we present the Charlotte Anomaly Dataset (CHAD). CHAD is a high-resolution, multi-camera anomaly dataset in a commercial parking lot setting. In addition to frame-level anomaly labels, CHAD is the first anomaly dataset to include bounding box, identity, and pose annotations for each actor. This is especially beneficial for skeleton-based anomaly detection, which is useful for its lower computational demand in real-world settings. CHAD is also the first anomaly dataset to contain multiple views of the same scene. With four camera views and over 1.15 million frames, CHAD is the largest fully annotated anomaly detection dataset including person annotations, collected from continuous video streams from stationary cameras for smart video surveillance applications. To demonstrate the efficacy of CHAD for training and evaluation, we benchmark two state-of-the-art skeleton-based anomaly detection algorithms on CHAD and provide comprehensive analysis, including both quantitative results and qualitative examination.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

With the rise of AI in recent years and the increase in complexity of the models, the growing demand in computational resources is starting to pose a significant challenge. The need for higher compute power is being met with increasingly more potent accelerators and the use of large compute clusters. However, the gain in prediction accuracy from large models trained on distributed and accelerated systems comes at the price of a substantial increase in energy demand, and researchers have started questioning the environmental friendliness of such AI methods at scale. Consequently, energy efficiency plays an important role for AI model developers and infrastructure operators alike. The energy consumption of AI workloads depends on the model implementation and the utilized hardware. Therefore, accurate measurements of the power draw of AI workflows on different types of compute nodes is key to algorithmic improvements and the design of future compute clusters and hardware. To this end, we present measurements of the energy consumption of two typical applications of deep learning models on different types of compute nodes. Our results indicate that 1. deriving energy consumption directly from runtime is not accurate, but the consumption of the compute node needs to be considered regarding its composition; 2. neglecting accelerator hardware on mixed nodes results in overproportional inefficiency regarding energy consumption; 3. energy consumption of model training and inference should be considered separately - while training on GPUs outperforms all other node types regarding both runtime and energy consumption, inference on CPU nodes can be comparably efficient. One advantage of our approach is that the information on energy consumption is available to all users of the supercomputer, enabling an easy transfer to other workloads alongside a raise in user-awareness of energy consumption.

Neuromorphic computing using biologically inspired Spiking Neural Networks (SNNs) is a promising solution to meet Energy-Throughput (ET) efficiency needed for edge computing devices. Neuromorphic hardware architectures that emulate SNNs in analog/mixed-signal domains have been proposed to achieve order-of-magnitude higher energy efficiency than all-digital architectures, however at the expense of limited scalability, susceptibility to noise, complex verification, and poor flexibility. On the other hand, state-of-the-art digital neuromorphic architectures focus either on achieving high energy efficiency (Joules/synaptic operation (SOP)) or throughput efficiency (SOPs/second/area), resulting in poor ET efficiency. In this work, we present THOR, an all-digital neuromorphic processor with a novel memory hierarchy and neuron update architecture that addresses both energy consumption and throughput bottlenecks. We implemented THOR in 28nm FDSOI CMOS technology and our post-layout results demonstrate an ET efficiency of 7.29G $\text{TSOP}^2/\text{mm}^2\text{Js}$ at 0.9V, 400 MHz, which represents a 3X improvement over state-of-the-art digital neuromorphic processors.

Incivility remains a major challenge for online discussion platforms, to such an extent that even conversations between well-intentioned users can often derail into uncivil behavior. Traditionally, platforms have relied on moderators to -- with or without algorithmic assistance -- take corrective actions such as removing comments or banning users. In this work we propose a complementary paradigm that directly empowers users by proactively enhancing their awareness about existing tension in the conversation they are engaging in and actively guides them as they are drafting their replies to avoid further escalation. As a proof of concept for this paradigm, we design an algorithmic tool that provides such proactive information directly to users, and conduct a user study in a popular discussion platform. Through a mixed methods approach combining surveys with a randomized controlled experiment, we uncover qualitative and quantitative insights regarding how the participants utilize and react to this information. Most participants report finding this proactive paradigm valuable, noting that it helps them to identify tension that they may have otherwise missed and prompts them to further reflect on their own replies and to revise them. These effects are corroborated by a comparison of how the participants draft their reply when our tool warns them that their conversation is at risk of derailing into uncivil behavior versus in a control condition where the tool is disabled. These preliminary findings highlight the potential of this user-centered paradigm and point to concrete directions for future implementations.

To address the widespread problem of uncivil behavior, many online discussion platforms employ human moderators to take action against objectionable content, such as removing it or placing sanctions on its authors. This reactive paradigm of taking action against already-posted antisocial content is currently the most common form of moderation, and has accordingly underpinned many recent efforts at introducing automation into the moderation process. Comparatively less work has been done to understand other moderation paradigms -- such as proactively discouraging the emergence of antisocial behavior rather than reacting to it -- and the role algorithmic support can play in these paradigms. In this work, we investigate such a proactive framework for moderation in a case study of a collaborative setting: Wikipedia Talk Pages. We employ a mixed methods approach, combining qualitative and design components for a holistic analysis. Through interviews with moderators, we find that despite a lack of technical and social support, moderators already engage in a number of proactive moderation behaviors, such as preemptively intervening in conversations to keep them on track. Further, we explore how automation could assist with this existing proactive moderation workflow by building a prototype tool, presenting it to moderators, and examining how the assistance it provides might fit into their workflow. The resulting feedback uncovers both strengths and drawbacks of the prototype tool and suggests concrete steps towards further developing such assisting technology so it can most effectively support moderators in their existing proactive moderation workflow.