Reducing traffic accidents is a crucial global public safety concern. Accident prediction is key to improving traffic safety, enabling proactive measures to be taken before a crash occurs, and informing safety policies, regulations, and targeted interventions. Despite numerous studies on accident prediction over the past decades, many have limitations in terms of generalizability, reproducibility, or feasibility for practical use due to input data or problem formulation. To address existing shortcomings, we propose CrashFormer, a multi-modal architecture that utilizes comprehensive (but relatively easy to obtain) inputs such as the history of accidents, weather information, map images, and demographic information. The model predicts the future risk of accidents on a reasonably acceptable cadence (i.e., every six hours) for a geographical location of 5.161 square kilometers. CrashFormer is composed of five components: a sequential encoder to utilize historical accidents and weather data, an image encoder to use map imagery data, a raw data encoder to utilize demographic information, a feature fusion module for aggregating the encoded features, and a classifier that accepts the aggregated data and makes predictions accordingly. Results from extensive real-world experiments in 10 major US cities show that CrashFormer outperforms state-of-the-art sequential and non-sequential models by 1.8% in F1-score on average when using ``sparse'' input data.

Optimal transport aims to learn a mapping of sources to targets by minimizing the cost, which is typically defined as a function of distance. The solution to this problem consists of straight line segments optimally connecting sources to targets, and it does not exhibit branching. These optimal solutions are in stark contrast with both natural, and man-made transportation networks, where branching structures are prevalent. Here we discuss a fast heuristic branching method for optimal transport in networks. We also provide several numerical applications to synthetic examples, a simplified cardiovascular network, and the "Santa Claus" distribution network which includes 141,182 cities around the world, with known location and population.

Effective root cause analysis (RCA) is vital for swiftly restoring services, minimizing losses, and ensuring the smooth operation and management of complex systems. Previous data-driven RCA methods, particularly those employing causal discovery techniques, have primarily focused on constructing dependency or causal graphs for backtracking the root causes. However, these methods often fall short as they rely solely on data from a single modality, thereby resulting in suboptimal solutions. In this work, we propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. To explore intricate relationships across different modalities, we propose a contrastive learning-based approach to extract modality-invariant and modality-specific representations within a shared latent space. Additionally, we introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph. Finally, we employ random walk with restart to simulate system fault propagation and identify potential root causes. Extensive experiments on three real-world datasets validate the effectiveness of our proposed framework.

Algorithms for automatic piano transcription have improved dramatically in recent years due to new datasets and modeling techniques. Recent developments have focused primarily on adapting new neural network architectures, such as the Transformer and Perceiver, in order to yield more accurate systems. In this work, we study transcription systems from the perspective of their training data. By measuring their performance on out-of-distribution annotated piano data, we show how these models can severely overfit to acoustic properties of the training data. We create a new set of audio for the MAESTRO dataset, captured automatically in a professional studio recording environment via Yamaha Disklavier playback. Using various data augmentation techniques when training with the original and re-performed versions of the MAESTRO dataset, we achieve state-of-the-art note-onset accuracy of 88.4 F1-score on the MAPS dataset, without seeing any of its training data. We subsequently analyze these data augmentation techniques in a series of ablation studies to better understand their influence on the resulting models.

Quantum machine learning, focusing on quantum neural networks (QNNs), remains a vastly uncharted field of study. Current QNN models primarily employ variational circuits on an ansatz or a quantum feature map, often requiring multiple entanglement layers. This methodology not only increases the computational cost of the circuit beyond what is practical on near-term quantum devices but also misleadingly labels these models as neural networks, given their divergence from the structure of a typical feed-forward neural network (FFNN). Moreover, the circuit depth and qubit needs of these models scale poorly with the number of data features, resulting in an efficiency challenge for real-world machine-learning tasks. We introduce a bona fide QNN model, which seamlessly aligns with the versatility of a traditional FFNN in terms of its adaptable intermediate layers and nodes, absent from intermediate measurements such that our entire model is coherent. This model stands out with its reduced circuit depth and number of requisite C-NOT gates to outperform prevailing QNN models. Furthermore, the qubit count in our model remains unaffected by the data's feature quantity. We test our proposed model on various benchmarking datasets such as the diagnostic breast cancer (Wisconsin) and credit card fraud detection datasets. We compare the outcomes of our model with the existing QNN methods to showcase the advantageous efficacy of our approach, even with a reduced requirement on quantum resources. Our model paves the way for application of quantum neural networks to real relevant machine learning problems.

Biometrics involves using unique human traits, both physical and behavioral, for the digital identification of individuals to provide access to systems, devices, or information. Within the field of computer science, it acts as a method for identifying and verifying individuals and controlling access. While the conventional method for personal authentication involves passwords, the vulnerability arises when passwords are compromised, allowing unauthorized access to sensitive actions. Biometric authentication presents a viable answer to this problem and is the most secure and user-friendly authentication method. Today, fingerprints, iris and retina patterns, facial recognition, hand shapes, palm prints, and voice recognition are frequently used forms of biometrics. Despite the diverse nature of these biometric identifiers, the core objective remains consistent ensuring security, recognizing authorized users, and rejecting impostors. Hence, it is crucial to determine accurately whether the characteristics belong to the rightful person. For systems to be effective and widely accepted, the error rate in recognition and verification must approach zero. It is acknowledged that current biometric techniques, while advanced, are not infallible and require continuous improvement. A more refined classifier is deemed necessary to classify patterns accurately. Artificial Neural Networks, which simulate the human brain's operations, present themselves as a promising approach. The survey presented herein explores various biometric techniques based on neural networks, emphasizing the ongoing quest for enhanced accuracy and reliability. It concludes that The utilization of neural networks along with biometric features not only enhances accuracy but also contributes to overall better security.

Current approaches of knowledge editing struggle to effectively propagate updates to interconnected facts. In this work, we delve into the barriers that hinder the appropriate propagation of updated knowledge within these models for accurate reasoning. To support our analysis, we introduce a novel reasoning-based benchmark -- ReCoE (Reasoning-based Counterfactual Editing dataset) -- which covers six common reasoning schemes in real world. We conduct a thorough analysis of existing knowledge editing techniques, including input augmentation, finetuning, and locate-and-edit. We found that all model editing methods show notably low performance on this dataset, especially in certain reasoning schemes. Our analysis over the chain-of-thought generation of edited models further uncover key reasons behind the inadequacy of existing knowledge editing methods from a reasoning standpoint, involving aspects on fact-wise editing, fact recall ability, and coherence in generation. We will make our benchmark publicly available.

Abstract-- The execution failure of cyber-physical systems (e.g., autonomous driving systems, unmanned aerial systems, and robotic systems) could result in the loss of life, severe injuries, large-scale environmental damage, property destruction, and major economic loss. Hence, such systems usually require a strong justification that they will effectively support critical requirements (e.g., safety, security, and reliability) for which they were designed. Thus, it is often mandatory to develop compelling assurance cases to support that justification and allow regulatory bodies to certify such systems. In such contexts, detecting assurance deficits, relying on patterns to improve the structure of assurance cases, improving existing assurance case notations, and (semi-)automating the generation of assurance cases are key to develop compelling assurance cases and foster consumer acceptance. We therefore explore challenges related to such assurance enablers and outline some potential directions that could be explored to tackle them.

Prompts are crucial to large language models as they provide context information such as topic or logical relationships. Inspired by this, we propose PromptASR, a framework that integrates prompts in end-to-end automatic speech recognition (E2E ASR) systems to achieve contextualized ASR with controllable style of transcriptions. Specifically, a dedicated text encoder encodes the text prompts and the encodings are injected into the speech encoder by cross-attending the features from two modalities. When using the ground truth text from preceding utterances as content prompt, the proposed system achieves 21.9% and 6.8% relative word error rate reductions on a book reading dataset and an in-house dataset compared to a baseline ASR system. The system can also take word-level biasing lists as prompt to improve recognition accuracy on rare words. An additional style prompt can be given to the text encoder and guide the ASR system to output different styles of transcriptions. The code is available at icefall.

This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound matching, to replicate a given audio input. Notably, DiffMoog facilitates modulation capabilities (FM/AM), low-frequency oscillators (LFOs), filters, envelope shapers, and the ability for users to create custom signal chains. We introduce an open-source platform that comprises DiffMoog and an end-to-end sound matching framework. This framework utilizes a novel signal-chain loss and an encoder network that self-programs its outputs to predict DiffMoogs parameters based on the user-defined modular architecture. Moreover, we provide insights and lessons learned towards sound matching using differentiable synthesis. Combining robust sound capabilities with a holistic platform, DiffMoog stands as a premier asset for expediting research in audio synthesis and machine learning.