Understanding the structure of real data is paramount in advancing modern deep-learning methodologies. Natural data such as images are believed to be composed of features organised in a hierarchical and combinatorial manner, which neural networks capture during learning. Recent advancements show that diffusion models can generate high-quality images, hinting at their ability to capture this underlying structure. We study this phenomenon in a hierarchical generative model of data. We find that the backward diffusion process acting after a time $t$ is governed by a phase transition at some threshold time, where the probability of reconstructing high-level features, like the class of an image, suddenly drops. Instead, the reconstruction of low-level features, such as specific details of an image, evolves smoothly across the whole diffusion process. This result implies that at times beyond the transition, the class has changed but the generated sample may still be composed of low-level elements of the initial image. We validate these theoretical insights through numerical experiments on class-unconditional ImageNet diffusion models. Our analysis characterises the relationship between time and scale in diffusion models and puts forward generative models as powerful tools to model combinatorial data properties.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
Markov
·
馬爾可夫過程
·
INFORMS
·
講稿
·
Markov processes serve as foundational models in many scientific disciplines, such as molecular dynamics, and their simulation forms a common basis for analysis. While simulations produce useful trajectories, obtaining macroscopic information directly from microstate data presents significant challenges. This paper addresses this gap by introducing the concept of membership functions being the macrostates themselves. We derive equations for the holding times of these macrostates and demonstrate their consistency with the classical definition. Furthermore, we discuss the application of the ISOKANN method for learning these quantities from simulation data. In addition, we present a novel method for extracting transition paths based on the ISOKANN results and demonstrate its efficacy by applying it to simulations of the mu-opioid receptor. With this approach we provide a new perspective on analyzing the macroscopic behaviour of Markov systems.
The increasing growth of data volume, and the consequent explosion in demand for computational power, are affecting scientific computing, as shown by the rise of extreme data scientific workflows. As the need for computing power increases, quantum computing has been proposed as a way to deliver it. It may provide significant theoretical speedups for many scientific applications (i.e., molecular dynamics, quantum chemistry, combinatorial optimization, and machine learning). Therefore, integrating quantum computers into the computing continuum constitutes a promising way to speed up scientific computation. However, the scientific computing community still lacks the necessary tools and expertise to fully harness the power of quantum computers in the execution of complex applications such as scientific workflows. In this work, we describe the main characteristics of quantum computing and its main benefits for scientific applications, then we formalize hybrid quantum-classic workflows, explore how to identify quantum components and map them onto resources. We demonstrate concepts on a real use case and define a software architecture for a hybrid workflow management system.
Robot swarms can effectively serve a variety of sensing and inspection applications. Certain inspection tasks require a binary classification decision. This work presents an experimental setup for a surface inspection task based on vibration sensing and studies a Bayesian two-outcome decision-making algorithm in a swarm of miniaturized wheeled robots. The robots are tasked with individually inspecting and collectively classifying a 1mx1m tiled surface consisting of vibrating and non-vibrating tiles based on the majority type of tiles. The robots sense vibrations using onboard IMUs and perform collision avoidance using a set of IR sensors. We develop a simulation and optimization framework leveraging the Webots robotic simulator and a Particle Swarm Optimization (PSO) method. We consider two existing information sharing strategies and propose a new one that allows the swarm to rapidly reach accurate classification decisions. We first find optimal parameters that allow efficient sampling in simulation and then evaluate our proposed strategy against the two existing ones using 100 randomized simulation and 10 real experiments. We find that our proposed method compels the swarm to make decisions at an accelerated rate, with an improvement of up to 20.52% in mean decision time at only 0.78% loss in accuracy.
Facial expression-based human emotion recognition is a critical research area in psychology and medicine. State-of-the-art classification performance is only reached by end-to-end trained neural networks. Nevertheless, such black-box models lack transparency in their decision-making processes, prompting efforts to ascertain the rules that underlie classifiers' decisions. Analyzing single inputs alone fails to expose systematic learned biases. These biases can be characterized as facial properties summarizing abstract information like age or medical conditions. Therefore, understanding a model's prediction behavior requires an analysis rooted in causality along such selected properties. We demonstrate that up to 91.25% of classifier output behavior changes are statistically significant concerning basic properties. Among those are age, gender, and facial symmetry. Furthermore, the medical usage of surface electromyography significantly influences emotion prediction. We introduce a workflow to evaluate explicit properties and their impact. These insights might help medical professionals select and apply classifiers regarding their specialized data and properties.
Systems for multimodal emotion recognition (MMER) can typically outperform unimodal systems by leveraging the inter- and intra-modal relationships between, e.g., visual, textual, physiological, and auditory modalities. In this paper, an MMER method is proposed that relies on a joint multimodal transformer for fusion with key-based cross-attention. This framework aims to exploit the diverse and complementary nature of different modalities to improve predictive accuracy. Separate backbones capture intra-modal spatiotemporal dependencies within each modality over video sequences. Subsequently, a joint multimodal transformer fusion architecture integrates the individual modality embeddings, allowing the model to capture inter-modal and intra-modal relationships effectively. Extensive experiments on two challenging expression recognition tasks: (1) dimensional emotion recognition on the Affwild2 dataset (with face and voice), and (2) pain estimation on the Biovid dataset (with face and biosensors), indicate that the proposed method can work effectively with different modalities. Empirical results show that MMER systems with our proposed fusion method allow us to outperform relevant baseline and state-of-the-art methods.
A novel topological-data-analytical (TDA) method is proposed to distinguish, from noise, small holes surrounded by high-density regions of a probability density function. The proposed method is robust against additive noise and outliers. Traditional TDA tools, like those based on the distance filtration, often struggle to distinguish small features from noise, because both have short persistences. An alternative filtration, called the Robust Density-Aware Distance (RDAD) filtration, is proposed to prolong the persistences of small holes of high-density regions. This is achieved by weighting the distance function by the density in the sense of Bell et al. The concept of distance-to-measure is incorporated to enhance stability and mitigate noise. The persistence-prolonging property and robustness of the proposed filtration are rigorously established, and numerical experiments are presented to demonstrate the proposed filtration's utility in identifying small holes.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.
The generalization mystery in deep learning is the following: Why do over-parameterized neural networks trained with gradient descent (GD) generalize well on real datasets even though they are capable of fitting random datasets of comparable size? Furthermore, from among all solutions that fit the training data, how does GD find one that generalizes well (when such a well-generalizing solution exists)? We argue that the answer to both questions lies in the interaction of the gradients of different examples during training. Intuitively, if the per-example gradients are well-aligned, that is, if they are coherent, then one may expect GD to be (algorithmically) stable, and hence generalize well. We formalize this argument with an easy to compute and interpretable metric for coherence, and show that the metric takes on very different values on real and random datasets for several common vision networks. The theory also explains a number of other phenomena in deep learning, such as why some examples are reliably learned earlier than others, why early stopping works, and why it is possible to learn from noisy labels. Moreover, since the theory provides a causal explanation of how GD finds a well-generalizing solution when one exists, it motivates a class of simple modifications to GD that attenuate memorization and improve generalization. Generalization in deep learning is an extremely broad phenomenon, and therefore, it requires an equally general explanation. We conclude with a survey of alternative lines of attack on this problem, and argue that the proposed approach is the most viable one on this basis.
Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for NMT.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191