在过去的几年里，已经表明，深度学习系统在对抗性示例的攻击中非常脆弱。基于神经网络的自动语音识别（ASR）系统也不例外。有针对性的和未确定的攻击可以以这样的方式修改音频输入信号，使得人类仍然识别相同的单词，而ASR系统被转向以预测不同的转录。在本文中，我们提出了一种防御机制，该防御机制通过在向ASR系统馈送输入之前，通过应用慢速特征分析，低通滤波器或两者来删除来自音频信号的快速变化功能。我们对在这种方式预处理的数据训练的混合ASR模型进行了实证分析。虽然所产生的模型在良性数据上表现得非常好，但它们对针对性的对抗攻击进行了更高的稳健性：我们的最终建议的模型显示了与基线模型类似的清洁数据的性能，同时具有比较强大的四倍。

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.

State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications. Previous work fails to produce explanations for both bounding box and classification decisions, and generally make individual explanations for various detectors. In this paper, we propose an open-source Detector Explanation Toolkit (DExT) which implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. We suggests various multi-object visualization methods to merge the explanations of multiple objects detected in an image as well as the corresponding detections in a single image. The quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. Both quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. We expect that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions.

The mediocre performance of conventional federated learning (FL) over heterogeneous data has been facilitating personalized FL solutions, where, unlike conventional FL which trains a single global consensus model, different models are allowed for different clients. However, in most existing personalized FL algorithms, the collaborative knowledge across the federation was only implicitly passed to the clients in ways such as model aggregation or regularization. We observed that this implicit knowledge transfer fails to maximize the potential value of each client's empirical risk toward other clients. Based on our observation, in this work, we propose Personalized Global Federated Learning (PGFed), a novel personalized FL framework that enables each client to personalize its own global objective by explicitly and adaptively aggregating the empirical risks of itself and other clients. To avoid massive ($O(N^2)$) communication overhead and potential privacy leakage, each client's risk is estimated through a first-order approximation for other clients' adaptive risk aggregation. On top of PGFed, we develop a momentum upgrade, dubbed PGFedMo, to more efficiently utilize clients' empirical risks. Our extensive experiments under different federated settings with benchmark datasets show consistent improvements of PGFed over the compared state-of-the-art alternatives.

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any changes to the outputs, by computing several tokens in parallel. At the heart of our approach lie the observations that (1) hard language-modeling tasks often include easier subtasks that can be approximated well by more efficient models, and (2) using speculative execution and a novel sampling method, we can make exact decoding from the large models faster, by running them in parallel on the outputs of the approximation models, potentially generating several tokens concurrently, and without changing the distribution. Our method supports existing off-the-shelf models without retraining or architecture changes. We demonstrate it on T5-XXL and show a 2X-3X acceleration compared to the standard T5X implementation, with identical outputs.

Trusting the predictions of deep learning models in safety critical settings such as the medical domain is still not a viable option. Distentangled uncertainty quantification in the field of medical imaging has received little attention. In this paper, we study disentangled uncertainties in image to image translation tasks in the medical domain. We compare multiple uncertainty quantification methods, namely Ensembles, Flipout, Dropout, and DropConnect, while using CycleGAN to convert T1-weighted brain MRI scans to T2-weighted brain MRI scans. We further evaluate uncertainty behavior in the presence of out of distribution data (Brain CT and RGB Face Images), showing that epistemic uncertainty can be used to detect out of distribution inputs, which should increase reliability of model outputs.

Safety-critical applications like autonomous driving use Deep Neural Networks (DNNs) for object detection and segmentation. The DNNs fail to predict when they observe an Out-of-Distribution (OOD) input leading to catastrophic consequences. Existing OOD detection methods were extensively studied for image inputs but have not been explored much for LiDAR inputs. So in this study, we proposed two datasets for benchmarking OOD detection in 3D semantic segmentation. We used Maximum Softmax Probability and Entropy scores generated using Deep Ensembles and Flipout versions of RandLA-Net as OOD scores. We observed that Deep Ensembles out perform Flipout model in OOD detection with greater AUROC scores for both datasets.

Increasingly high-stakes decisions are made using neural networks in order to make predictions. Specifically, meteorologists and hedge funds apply these techniques to time series data. When it comes to prediction, there are certain limitations for machine learning models (such as lack of expressiveness, vulnerability of domain shifts and overconfidence) which can be solved using uncertainty estimation. There is a set of expectations regarding how uncertainty should ``behave". For instance, a wider prediction horizon should lead to more uncertainty or the model's confidence should be proportional to its accuracy. In this paper, different uncertainty estimation methods are compared to forecast meteorological time series data and evaluate these expectations. The results show how each uncertainty estimation method performs on the forecasting task, which partially evaluates the robustness of predicted uncertainty.

过度拟合和概括是机器学习中的一个重要概念，因为只有对通用应用程序进行概括的模型才是有趣的。然而，一些学生难以通过讲座和练习来学习这个重要的概念。在本文中，我们描述了学生误解过度拟合的常见例子，并为可能的解决方案提供了建议。我们涵盖了学生对过度拟合，过度拟合解决方案的误解以及通常与过度拟合问题相混淆的实施错误。我们希望我们的论文可以有助于提高学生对这个重要主题的理解和讲座。

本文提出了一种通过深层插件（PNP）方法恢复数字视频的新方法。在贝叶斯形式主义下，该方法包括在交替的优化方案中使用深度卷积的降级网络代替先前的近端操作员。我们通过直接应用该方法来恢复降级视频观察结果的数字视频，从而将自己与先前的PNP工作区分开来。这样，可以将经过验证训练的网络重新用于其他视频修复任务。我们在视频脱张，超分辨率和随机缺失像素的插值方面的实验都显示出明显的好处，因为它使用专门为视频denoising设计的网络，因为它可以产生更好的恢复性能和更好的时间稳定性。使用相同的PNP公式。此外，我们的方法比较比较在序列的每个帧上分别应用不同的最新PNP方案。这在视频修复领域打开了新的观点。