Data-driven modeling approaches such as jump tables are promising techniques to model populations of resistive random-access memory (ReRAM) or other emerging memory devices for hardware neural network simulations. As these tables rely on data interpolation, this work explores the open questions about their fidelity in relation to the stochastic device behavior they model. We study how various jump table device models impact the attained network performance estimates, a concept we define as modeling bias. Two methods of jump table device modeling, binning and Optuna-optimized binning, are explored using synthetic data with known distributions for benchmarking purposes, as well as experimental data obtained from TiOx ReRAM devices. Results on a multi-layer perceptron trained on MNIST show that device models based on binning can behave unpredictably particularly at low number of points in the device dataset, sometimes over-promising, sometimes under-promising target network accuracy. This paper also proposes device level metrics that indicate similar trends with the modeling bias metric at the network level. The proposed approach opens the possibility for future investigations into statistical device models with better performance, as well as experimentally verified modeling bias in different in-memory computing and neural network architectures.

孟加拉语是世界上说话最多的语言之一，全球有超过3亿的演讲者。尽管它很受欢迎，但由于缺乏多样化的开源数据集，对孟加拉语音识别系统的发展的研究受到阻碍。作为前进的道路，我们已经众包孟加拉语音语音数据集，这是句子级自动语音识别语料库。该数据集于Mozilla Common Voice平台上收集，是正在进行的广告系列的一部分，该活动已在2个月内收集了超过400个小时的数据，并且正在迅速增长。我们的分析表明，与OpenSLR孟加拉ASR数据集相比，该数据集具有更多的发言人，音素和环境多样性，这是最大的现有开源孟加拉语语音数据集。我们提供从数据集获得的见解，并讨论未来版本中需要解决的关键语言挑战。此外，我们报告了一些自动语音识别（ASR）算法的当前性能，并为将来的研究设定了基准。

Human Activity Recognition (HAR) is an emerging technology with several applications in surveillance, security, and healthcare sectors. Noninvasive HAR systems based on Wi-Fi Channel State Information (CSI) signals can be developed leveraging the quick growth of ubiquitous Wi-Fi technologies, and the correlation between CSI dynamics and body motions. In this paper, we propose Principal Component-based Wavelet Convolutional Neural Network (or PCWCNN) -- a novel approach that offers robustness and efficiency for practical real-time applications. Our proposed method incorporates two efficient preprocessing algorithms -- the Principal Component Analysis (PCA) and the Discrete Wavelet Transform (DWT). We employ an adaptive activity segmentation algorithm that is accurate and computationally light. Additionally, we used the Wavelet CNN for classification, which is a deep convolutional network analogous to the well-studied ResNet and DenseNet networks. We empirically show that our proposed PCWCNN model performs very well on a real dataset, outperforming existing approaches.

Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classification network. In this work, we propose a novel attack technique called Sparse Adversarial and Interpretable Attack Framework (SAIF). Specifically, we design imperceptible attacks that contain low-magnitude perturbations at a small number of pixels and leverage these sparse attacks to reveal the vulnerability of classifiers. We use the Frank-Wolfe (conditional gradient) algorithm to simultaneously optimize the attack perturbations for bounded magnitude and sparsity with $O(1/\sqrt{T})$ convergence. Empirical results show that SAIF computes highly imperceptible and interpretable adversarial examples, and outperforms state-of-the-art sparse attack methods on the ImageNet dataset.

Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions associated with the faulty behavior? Recent works on decomposing a fully connected neural network (FCNN) and convolutional neural network (CNN) into modules have shown the value of engineering deep models in this manner, which is standard in traditional SE but foreign for deep learning models. However, prior works focus on the image-based multiclass classification problems and cannot be applied to RNN due to (a) different layer structures, (b) loop structures, (c) different types of input-output architectures, and (d) usage of both nonlinear and logistic activation functions. In this work, we propose the first approach to decompose an RNN into modules. We study different types of RNNs, i.e., Vanilla, LSTM, and GRU. Further, we show how such RNN modules can be reused and replaced in various scenarios. We evaluate our approach against 5 canonical datasets (i.e., Math QA, Brown Corpus, Wiki-toxicity, Clinc OOS, and Tatoeba) and 4 model variants for each dataset. We found that decomposing a trained model has a small cost (Accuracy: -0.6%, BLEU score: +0.10%). Also, the decomposed modules can be reused and replaced without needing to retrain.

Recent advances in pixel-level tasks (e.g., segmentation) illustrate the benefit of long-range interactions between aggregated region-based representations that can enhance local features. However, such pixel-to-region associations and the resulting representation, which often take the form of attention, cannot model the underlying semantic structure of the scene (e.g., individual objects and, by extension, their interactions). In this work, we take a step toward addressing this limitation. Specifically, we propose an architecture where we learn to project image features into latent region representations and perform global reasoning across them, using a transformer, to produce contextualized and scene-consistent representations that are then fused with original pixel-level features. Our design enables the latent regions to represent semantically meaningful concepts, by ensuring that activated regions are spatially disjoint and unions of such regions correspond to connected object segments. The resulting semantic global reasoning (SGR) is end-to-end trainable and can be combined with any semantic segmentation framework and backbone. Combining SGR with DeepLabV3 results in a semantic segmentation performance that is competitive to the state-of-the-art, while resulting in more semantically interpretable and diverse region representations, which we show can effectively transfer to detection and instance segmentation. Further, we propose a new metric that allows us to measure the semantics of representations at both the object class and instance level.

We introduce an information-maximization approach for the Generalized Category Discovery (GCD) problem. Specifically, we explore a parametric family of loss functions evaluating the mutual information between the features and the labels, and find automatically the one that maximizes the predictive performances. Furthermore, we introduce the Elbow Maximum Centroid-Shift (EMaCS) technique, which estimates the number of classes in the unlabeled set. We report comprehensive experiments, which show that our mutual information-based approach (MIB) is both versatile and highly competitive under various GCD scenarios. The gap between the proposed approach and the existing methods is significant, more so when dealing with fine-grained classification problems. Our code: \url{https://github.com/fchiaroni/Mutual-Information-Based-GCD}.

Non-negative matrix factorization is a popular unsupervised machine learning algorithm for extracting meaningful features from data which are inherently non-negative. However, such data sets may often contain privacy-sensitive user data, and therefore, we may need to take necessary steps to ensure the privacy of the users while analyzing the data. In this work, we focus on developing a Non-negative matrix factorization algorithm in the privacy-preserving framework. More specifically, we propose a novel privacy-preserving algorithm for non-negative matrix factorisation capable of operating on private data, while achieving results comparable to those of the non-private algorithm. We design the framework such that one has the control to select the degree of privacy grantee based on the utility gap. We show our proposed framework's performance in six real data sets. The experimental results show that our proposed method can achieve very close performance with the non-private algorithm under some parameter regime, while ensuring strict privacy.

机器学习和深度学习模型需要大量的培训过程数据，在某些情况下，可能会有一些敏感数据，例如涉及的客户信息，组织可能会犹豫要外包模型构建。一些隐私保护技术，例如差异隐私，同构加密和安全的多方计算，可以与不同的机器学习和深度学习算法集成，以为数据以及模型提供安全性。在本文中，我们建议使用完全同构的加密加密进行混乱的极端学习机及其加密形式，其中使用逻辑图而不是均匀分布生成权重和偏见。我们提出的方法在大多数数据集中都可以更好地或类似于传统的极限学习机器。

基于Centroid的聚类方法，例如K-均值，K-Medoids和K-Centers在探索性数据分析中被大量应用作为首选工具。在许多情况下，这些方法用于获得数据歧管的代表性质心，以可视化或摘要数据集。现实世界的数据集通常包含固有的异常情况，例如重复样本和采样偏见，表现出不平衡的聚类。我们建议通过对质心形成的群集引入最大半径约束$ r $来纠正这种情况，即，从同一集群中的样本则不应以$ \ ell_2 $距离的价格分开超过$ 2R $。我们通过求解半明确程序来实现此约束，然后是二次约束的线性分配问题。通过定性结果，我们表明我们提出的方法对数据集的不平衡和采样伪像是可靠的。据我们所知，我们的是第一个受到严格半径约束的约束K-均值聚类方法。 https://bit.ly/kmeans限制的代码