Convolutional neural networks are now seeing widespread use in a variety of fields, including image classification, facial and object recognition, medical imaging analysis, and many more. In addition, there are applications such as physics-informed simulators in which accurate forecasts in real time with a minimal lag are required. The present neural network designs include millions of parameters, which makes it difficult to install such complex models on devices that have limited memory. Compression techniques might be able to resolve these issues by decreasing the size of CNN models that are created by reducing the number of parameters that contribute to the complexity of the models. We propose a compressed tensor format of convolutional layer, a priori, before the training of the neural network. 3-way kernels or 2-way kernels in convolutional layers are replaced by one-way fiters. The overfitting phenomena will be reduced also. The time needed to make predictions or time required for training using the original Convolutional Neural Networks model would be cut significantly if there were fewer parameters to deal with. In this paper we present a method of a priori compressing convolutional neural networks for finite element (FE) predictions of physical data. Afterwards we validate our a priori compressed models on physical data from a FE model solving a 2D wave equation. We show that the proposed convolutinal compression technique achieves equivalent performance as classical convolutional layers with fewer trainable parameters and lower memory footprint.

Attitude is omnipresent in almost every type of text. There has yet to be any relevant research on attitudinal shifts in self-translation. The Chinese version of Between Tears and Laughter is a rare case of self-translation and co-translation in that the first 11 chapters are self-translated by Lin Yutang, and the last 12 chapters by Xu Chengbin. The current study conducted a word frequency analysis of this book's English and Chinese versions with LIWC and AntConc, and made comparative research into Lin Yutang's attitudinal changes. The results show that due to different writing purposes and readerships, there is less anger in Lin's self-translation (M=0.7755, SD=0.3861), which is a significant difference (t=2.2892, This attitudinal change is also reflected in the translations of some n-grams containing anger words. In contrast, there is no significant difference (t=1.88, This paper believes that corpus tools can help co-translators keep their translation consistent in attitude. Introduction Lin Yutang (1895 - 1976), the author of My Country and My People and Moment in Peking, was a world-renowned Chinese writer publishing novels, essays, translations, textbooks, and Chinese-English dictionaries, making outstanding achievements in literature, translation, and language research. He even invented a Chinese typewriter. He wrote more than 30 books in English, most of which describe China's cultural aspects. According to the biography of Lin Yutang written by his daughter Lin Taiyi, Lin was nominated twice for the Nobel Prize for Literature (Lin 1989).

The advances of Generative AI models with interactive capabilities over the past few years offer unique opportunities for socioeconomic mobility. Their potential for scalability, accessibility, affordability, personalizing and convenience sets a first-class opportunity for poverty-stricken countries to adapt and modernize their educational order. As a result, this position paper makes the case for an educational policy framework that would succeed in this transformation by prioritizing vocational and technical training over academic education in sub-Saharan African countries. We highlight substantial applications of Large Language Models, tailor-made to their respective cultural background(s) and needs, that would reinforce their systemic decolonization. Lastly, we provide specific historical examples of diverse states successfully implementing such policies in the elementary steps of their socioeconomic transformation, in order to corroborate our proposal to sub-Saharan African countries to follow their lead.

IoT networks are increasingly becoming target of sophisticated new cyber-attacks. Anomaly-based detection methods are promising in finding new attacks, but there are certain practical challenges like false-positive alarms, hard to explain, and difficult to scale cost-effectively. The IETF recent standard called Manufacturer Usage Description (MUD) seems promising to limit the attack surface on IoT devices by formally specifying their intended network behavior. In this paper, we use SDN to enforce and monitor the expected behaviors of each IoT device, and train one-class classifier models to detect volumetric attacks. Our specific contributions are fourfold. (1) We develop a multi-level inferencing model to dynamically detect anomalous patterns in network activity of MUD-compliant traffic flows via SDN telemetry, followed by packet inspection of anomalous flows. This provides enhanced fine-grained visibility into distributed and direct attacks, allowing us to precisely isolate volumetric attacks with microflow (5-tuple) resolution. (2) We collect traffic traces (benign and a variety of volumetric attacks) from network behavior of IoT devices in our lab, generate labeled datasets, and make them available to the public. (3) We prototype a full working system (modules are released as open-source), demonstrates its efficacy in detecting volumetric attacks on several consumer IoT devices with high accuracy while maintaining low false positives, and provides insights into cost and performance of our system. (4) We demonstrate how our models scale in environments with a large number of connected IoTs (with datasets collected from a network of IP cameras in our university campus) by considering various training strategies (per device unit versus per device type), and balancing the accuracy of prediction against the cost of models in terms of size and training time.

Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the within-class variability of final hidden layer outputs is infinitesimally small and their class means form a simplex equiangular tight frame. This simplifies the last layer behaviour to that of a nearest-class center decision rule. Despite the simplicity of this state, the dynamics and implications of reaching it are yet to be fully understood. In this work, we review the principles which aid in modelling neural collapse, followed by the implications of this state on generalization and transfer learning capabilities of neural networks. Finally, we conclude by discussing potential avenues and directions for future research.

Large language models (LLMs) have shown incredible capabilities and transcended the natural language processing (NLP) community, with adoption throughout many services like healthcare, therapy, education, and customer service. Since users include people with critical information needs like students or patients engaging with chatbots, the safety of these systems is of prime importance. Therefore, a clear understanding of the capabilities and limitations of LLMs is necessary. To this end, we systematically evaluate toxicity in over half a million generations of ChatGPT, a popular dialogue-based LLM. We find that setting the system parameter of ChatGPT by assigning it a persona, say that of the boxer Muhammad Ali, significantly increases the toxicity of generations. Depending on the persona assigned to ChatGPT, its toxicity can increase up to 6x, with outputs engaging in incorrect stereotypes, harmful dialogue, and hurtful opinions. This may be potentially defamatory to the persona and harmful to an unsuspecting user. Furthermore, we find concerning patterns where specific entities (e.g., certain races) are targeted more than others (3x more) irrespective of the assigned persona, that reflect inherent discriminatory biases in the model. We hope that our findings inspire the broader AI community to rethink the efficacy of current safety guardrails and develop better techniques that lead to robust, safe, and trustworthy AI systems.

Data-driven intelligent computational design (DICD) is a research hotspot emerged under the context of fast-developing artificial intelligence. It emphasizes on utilizing deep learning algorithms to extract and represent the design features hidden in historical or fabricated design process data, and then learn the combination and mapping patterns of these design features for the purposes of design solution retrieval, generation, optimization, evaluation, etc. Due to its capability of automatically and efficiently generating design solutions and thus supporting human-in-the-loop intelligent and innovative design activities, DICD has drawn the attentions from both academic and industrial fields. However, as an emerging research subject, there are still many unexplored issues that limit the development and application of DICD, such as specific dataset building, engineering design related feature engineering, systematic methods and techniques for DICD implementation in the entire product design process, etc. In this regard, a systematic and operable road map for DICD implementation from full-process perspective is established, including a general workflow for DICD project planning, an overall framework for DICD project implementation, the computing mechanisms for DICD implementation, key enabling technologies for detailed DICD implementation, and three application scenarios of DICD. The road map reveals the common mechanisms and calculation principles of existing DICD researches, and thus it can provide systematic guidance for the possible DICD applications that have not been explored.

Abstract-- This paper addresses the following research question: "can one compress a detailed 3D representation and use it directly for point cloud registration?". Map compression of the scene can be achieved by the tensor train (TT) decomposition of the signed distance function (SDF) representation. It regulates the amount of data reduced by the so-called TT-ranks. Using this representation we have proposed an algorithm, the TT-SDF2PC, that is capable of directly registering a PC to the compressed SDF by making use of efficient calculations of its derivatives in the TT domain, saving computations and memory. We compare TT-SDF2PC with SOTA local and global registration methods in a synthetic dataset and a real dataset and show on par performance while requiring significantly less resources.

Accurate state-of-health (SOH) estimation is critical to guarantee the safety, efficiency and reliability of battery-powered applications. Most SOH estimation methods focus on the 0-100\% full state-of-charge (SOC) range that has similar distributions. However, the batteries in real-world applications usually work in the partial SOC range under shallow-cycle conditions and follow different degradation profiles with no labeled data available, thus making SOH estimation challenging. To estimate shallow-cycle battery SOH, a novel unsupervised deep transfer learning method is proposed to bridge different domains using self-attention distillation module and multi-kernel maximum mean discrepancy technique. The proposed method automatically extracts domain-variant features from charge curves to transfer knowledge from the large-scale labeled full cycles to the unlabeled shallow cycles. The CALCE and SNL battery datasets are employed to verify the effectiveness of the proposed method to estimate the battery SOH for different SOC ranges, temperatures, and discharge rates. The proposed method achieves a root-mean-square error within 2\% and outperforms other transfer learning methods for different SOC ranges. When applied to batteries with different operating conditions and from different manufacturers, the proposed method still exhibits superior SOH estimation performance. The proposed method is the first attempt at accurately estimating battery SOH under shallow-cycle conditions without needing a full-cycle characteristic test.

Deep Neural Networks (DNNs) are built using artificial neural networks. They are part of machine learning methods that are capable of learning from data that have been used in a wide range of applications. DNNs are mainly handcrafted and they usually contain numerous layers. Research frontier has emerged that concerns automated construction of DNNs via evolutionary algorithms. This paper emphasizes the importance of what we call two-dimensional brain evolution and how it can inspire two dimensional DNN evolutionary modeling. We also highlight the connection between the dropout method which is widely-used in regularizing DNNs and neurogenesis of the brain, and how these concepts could benefit DNNs evolution.The paper concludes with several recommendations for enhancing the automatic construction of DNNs.