Hong Zhao

Hung Q. Vo, Huy Q. Vo, Son T. Ly et al.

Conventional tissue image analysis software provides foundational capabilities for cellular analysis, including segmentation, basic morphological feature extraction, and spatial organization analysis. However, these tools often require manual intervention and are not well integrated with code-driven automation, limiting efficiency and scalability for complex spatial tissue studies. In addition, they offer limited flexibility for custom analyses, as they typically support only a fixed set of pre-implemented spatial cellular features. To address these limitations, we propose CodeCytos, a coding-based reasoning agent framework that enables dynamic, programmable interaction with spatial molecular imaging data to improve automation and customization. CodeCytos is designed to streamline the exploration of custom spatial cellular features and adapt to diverse research needs. We demonstrate its utility through case studies on four expert-curated datasets from distinct tissue types: frontal cortex, non-small-cell lung cancer, pancreas, and tonsil. We evaluate CodeCytos under a realistic minimal prompt setting, where bioscientists pose simple questions without task-specific instructions or contextual information about spatial cellular analysis, and benchmark multiple LLM backbones with strong coding capabilities. We further show that incorporating tailored, domain-agnostic few-shot in-context coding-reasoning examples (randomly sampled demonstrations outside the spatial analysis domain) can substantially improve performance without requiring costly, expert-crafted in-domain demonstrations. Overall, CodeCytos outperforms baseline approaches, highlighting the potential of code-action agents to assist with custom feature exploration in spatial molecular imaging and to accelerate biomarker discovery.

Wei Miao, Hong Zhao, Tongjia Chen et al.

Recent stereo matching networks achieves dramatic performance by introducing epipolar line constraint to limit the matching range of dual-view. However, in complicated real-world scenarios, the feature information based on intra-epipolar line alone is too weak to facilitate stereo matching. In this paper, we present a simple but highly effective network called Alternated Attention U-shaped Transformer (AAUformer) to balance the impact of epipolar line in dual and single view respectively for excellent generalization performance. Compared to other models, our model has several main designs: 1) to better liberate the local semantic features of the single-view at pixel level, we introduce window self-attention to break the limits of intra-row self-attention and completely replace the convolutional network for denser features before cross-matching; 2) the multi-scale alternated attention backbone network was designed to extract invariant features in order to achieves the coarse-to-fine matching process for hard-to-discriminate regions. We performed a series of both comparative studies and ablation studies on several mainstream stereo matching datasets. The results demonstrate that our model achieves state-of-the-art on the Scene Flow dataset, and the fine-tuning performance is competitive on the KITTI 2015 dataset. In addition, for cross generalization experiments on synthetic and real-world datasets, our model outperforms several state-of-the-art works.

Yuchen Lin, Yong Zhang, Sihan Feng et al.

Advancements in artificial intelligence call for a deeper understanding of the fundamental mechanisms underlying deep learning. In this work, we propose a theoretical framework to analyze learning dynamics through the lens of dynamical systems theory. We redefine the notions of linearity and nonlinearity in neural networks by introducing two fundamental transformation units at the neuron level: order-preserving transformations and non-order-preserving transformations. Different transformation modes lead to distinct collective behaviors in weight vector organization, different modes of information extraction, and the emergence of qualitatively different learning phases. Transitions between these phases may occur during training, accounting for key phenomena such as grokking. To further characterize generalization and structural stability, we introduce the concept of attraction basins in both sample and weight spaces. The distribution of neurons with different transformation modes across layers, along with the structural characteristics of the two types of attraction basins, forms a set of core metrics for analyzing the performance of learning models. Hyperparameters such as depth, width, learning rate, and batch size act as control variables for fine-tuning these metrics. Our framework not only sheds light on the intrinsic advantages of deep learning, but also provides a novel perspective for optimizing network architectures and training strategies.

Hong Zhao, Huyunting Huang, Tonglin Zhang et al.

A 3D point cloud is an unstructured, sparse, and irregular dataset, typically collected by airborne LiDAR systems over a geological region. Laser pulses emitted from these systems reflect off objects both on and above the ground, resulting in a dataset containing the longitude, latitude, and elevation of each point, as well as information about the corresponding laser pulse strengths. A widely studied research problem, addressed in many previous works, is ground filtering, which involves partitioning the points into ground and non-ground subsets. This research introduces a novel task: detecting and identifying human-made objects amidst natural tree structures. This task is performed on the subset of non-ground points derived from the ground filtering stage. Marked Point Fields (MPFs) are used as models well-suited to these tasks. The proposed methodology consists of three stages: ground filtering, local information extraction (LIE), and clustering. In the ground filtering stage, a statistical method called One-Sided Regression (OSR) is introduced, addressing the limitations of prior ground filtering methods on uneven terrains. In the LIE stage, unsupervised learning methods are lacking. To mitigate this, a kernel-based method for the Hessian matrix of the MPF is developed. In the clustering stage, the Gaussian Mixture Model (GMM) is applied to the results of the LIE stage to partition the non-ground points into trees and human-made objects. The underlying assumption is that LiDAR points from trees exhibit a three-dimensional distribution, while those from human-made objects follow a two-dimensional distribution. The Hessian matrix of the MPF effectively captures this distinction. Experimental results demonstrate that the proposed ground filtering method outperforms previous techniques, and the LIE method successfully distinguishes between points representing trees and human-made objects.

Hong Zhao, Jin Wei-Kocsis, Adel Heidari Akhijahani et al.

Driven by advancements in sensing and computing, deep reinforcement learning (DRL)-based methods have demonstrated significant potential in effectively tackling distribution system restoration (DSR) challenges under uncertain operational scenarios. However, the data-intensive nature of DRL poses obstacles in achieving satisfactory DSR solutions for large-scale, complex distribution systems. Inspired by the transformative impact of emerging foundation models, including large language models (LLMs), across various domains, this paper explores an innovative approach harnessing LLMs' powerful computing capabilities to address scalability challenges inherent in conventional DRL methods for solving DSR. To our knowledge, this study represents the first exploration of foundation models, including LLMs, in revolutionizing conventional DRL applications in power system operations. Our contributions are twofold: 1) introducing a novel LLM-powered Physics-Informed Decision Transformer (PIDT) framework that leverages LLMs to transform conventional DRL methods for DSR operations, and 2) conducting comparative studies to assess the performance of the proposed LLM-powered PIDT framework at its initial development stage for solving DSR problems. While our primary focus in this paper is on DSR operations, the proposed PIDT framework can be generalized to optimize sequential decision-making across various power system operations.

Zhan Zhang, Qin Zhang, Yang Jiao et al.

AI-aided clinical diagnosis is desired in medical care. Existing deep learning models lack explainability and mainly focus on image analysis. The recently developed Dynamic Uncertain Causality Graph (DUCG) approach is causality-driven, explainable, and invariant across different application scenarios, without problems of data collection, labeling, fitting, privacy, bias, generalization, high cost and high energy consumption. Through close collaboration between clinical experts and DUCG technicians, 46 DUCG models covering 54 chief complaints were constructed. Over 1,000 diseases can be diagnosed without triage. Before being applied in real-world, the 46 DUCG models were retrospectively verified by third-party hospitals. The verified diagnostic precisions were no less than 95%, in which the diagnostic precision for every disease including uncommon ones was no less than 80%. After verifications, the 46 DUCG models were applied in the real-world in China. Over one million real diagnosis cases have been performed, with only 17 incorrect diagnoses identified. Due to DUCG's transparency, the mistakes causing the incorrect diagnoses were found and corrected. The diagnostic abilities of the clinicians who applied DUCG frequently were improved significantly. Following the introduction to the earlier presented DUCG methodology, the recommendation algorithm for potential medical checks is presented and the key idea of DUCG is extracted.

Ruixin Hong, Hongming Zhang, Hong Zhao et al.

Although large language models demonstrate remarkable question-answering performances, revealing the intermediate reasoning steps that the models faithfully follow remains challenging. In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps. The reasoning steps are organized as a structured entailment tree, which shows how premises are used to produce intermediate conclusions that can prove the correctness of the answer. We formulate the task as a discrete decision-making problem and solve it through the interaction of a reasoning environment and a controller. The environment is modular and contains several basic task-oriented modules, while the controller proposes actions to assemble the modules. Since the search space could be large, we introduce a Monte-Carlo planning algorithm to do a look-ahead search and select actions that will eventually lead to high-quality steps. FAME achieves state-of-the-art performance on the standard benchmark. It can produce valid and faithful reasoning steps compared with large language models with a much smaller model size.

Sihan Feng, Yong Zhang, Fuming Wang et al.

Despite their great success, neural networks still remain as black-boxes due to the lack of interpretability. Here we propose a new analyzing method, namely the weight pathway analysis (WPA), to make them transparent. We consider weights in pathways that link neurons longitudinally from input neurons to output neurons, or simply weight pathways, as the basic units for understanding a neural network, and decompose a neural network into a series of subnetworks of such weight pathways. A visualization scheme of the subnetworks is presented that gives longitudinal perspectives of the network like radiographs, making the internal structures of the network visible. Impacts of parameter adjustments or structural changes to the network can be visualized via such radiographs. Characteristic maps are established for subnetworks to characterize the enhancement or suppression of the influence of input samples on each output neuron. Using WPA, we discover that neural network store and utilize information in a holographic way, that is, subnetworks encode all training samples in a coherent structure and thus only by investigating the weight pathways can one explore samples stored in the network. Furthermore, with WPA, we reveal fundamental learning modes of a neural network: the linear learning mode and the nonlinear learning mode. The former extracts linearly separable features while the latter extracts linearly inseparable features. The hidden-layer neurons self-organize into different classes for establishing learning modes and for reaching the training goal. The finding of learning modes provides us the theoretical ground for understanding some of the fundamental problems of machine learning, such as the dynamics of learning process, the role of linear and nonlinear neurons, as well as the role of network width and depth.

Jiaxing Yan, Hong Zhao, Penghui Bu et al.

Self-supervised learning has shown very promising results for monocular depth estimation. Scene structure and local details both are significant clues for high-quality depth estimation. Recent works suffer from the lack of explicit modeling of scene structure and proper handling of details information, which leads to a performance bottleneck and blurry artefacts in predicted results. In this paper, we propose the Channel-wise Attention-based Depth Estimation Network (CADepth-Net) with two effective contributions: 1) The structure perception module employs the self-attention mechanism to capture long-range dependencies and aggregates discriminative features in channel dimensions, explicitly enhances the perception of scene structure, obtains the better scene understanding and rich feature representation. 2) The detail emphasis module re-calibrates channel-wise feature maps and selectively emphasizes the informative features, aiming to highlight crucial local details information and fuse different level features more efficiently, resulting in more precise and sharper depth prediction. Furthermore, the extensive experiments validate the effectiveness of our method and show that our model achieves the state-of-the-art results on the KITTI benchmark and Make3D datasets.

Hong Zhao

Given a segment of time series of a system at a particular set of parameter values, can one infers the global behavior of the system in its parameter space? Here we show that by using a learning machine we can achieve such a goal to a certain extent. It is found that following an appropriate training strategy that monotonously decreases the cost function, the learning machine in different training stage can mimic the system at different parameter set. Consequently, the global dynamical properties of the system is subsequently revealed, usually in the simple-to-complex order. The underlying mechanism is attributed to the training strategy, which causes the learning machine to collapse to a qualitatively equivalent system of the system behind the time series. Thus, the learning machine opens up a novel way to probe the global dynamical properties of a black-box system without artificially establish the equations of motion. The given illustrating examples include a representative model of low-dimensional nonlinear dynamical systems and a spatiotemporal model of reaction-diffusion systems.

Xiaowei Xu, Xiangao Jiang, Chunlian Ma et al.

We found that the real time reverse transcription-polymerase chain reaction (RT-PCR) detection of viral RNA from sputum or nasopharyngeal swab has a relatively low positive rate in the early stage to determine COVID-19 (named by the World Health Organization). The manifestations of computed tomography (CT) imaging of COVID-19 had their own characteristics, which are different from other types of viral pneumonia, such as Influenza-A viral pneumonia. Therefore, clinical doctors call for another early diagnostic criteria for this new type of pneumonia as soon as possible.This study aimed to establish an early screening model to distinguish COVID-19 pneumonia from Influenza-A viral pneumonia and healthy cases with pulmonary CT images using deep learning techniques. The candidate infection regions were first segmented out using a 3-dimensional deep learning model from pulmonary CT image set. These separated images were then categorized into COVID-19, Influenza-A viral pneumonia and irrelevant to infection groups, together with the corresponding confidence scores using a location-attention classification model. Finally the infection type and total confidence score of this CT case were calculated with Noisy-or Bayesian function.The experiments result of benchmark dataset showed that the overall accuracy was 86.7 % from the perspective of CT cases as a whole.The deep learning models established in this study were effective for the early screening of COVID-19 patients and demonstrated to be a promising supplementary diagnostic method for frontline clinical doctors.

Hong Zhao

We present that, instead of establishing the equations of motion, one can model-freely reveal the dynamical properties of a black-box system using a learning machine. Trained only by a segment of time series of a state variable recorded at present parameters values, the dynamics of the learning machine at different training stages can be mapped to the dynamics of the target system along a particular path in its parameter space, following an appropriate training strategy that monotonously decreases the cost function. This path is important, because along that, the primary dynamical properties of the target system will subsequently emerge, in the simple-to-complex order, matching closely the evolution law of certain self-evolved systems in nature. Why such a path can be reproduced is attributed to our training strategy. This particular function of the learning machine opens up a novel way to probe the global dynamical properties of a black-box system without artificially establish the equations of motion, and as such it might have countless applications. As an example, this method is applied to infer what dynamical stages a variable star has experienced and how it will evolve in future, by using the light curve observed presently.

Hong Zhao

Is it possible to generally construct a dynamical system to simulate a black system without recovering the equations of motion of the latter? Here we show that this goal can be approached by a learning machine. Trained by a set of input-output responses or a segment of time series of a black system, a learning machine can be served as a copy system to mimic the dynamics of various black systems. It can not only behave as the black system at the parameter set that the training data are made, but also recur the evolution history of the black system. As a result, the learning machine provides an effective way for prediction, and enables one to probe the global dynamics of a black system. These findings have significance for practical systems whose equations of motion cannot be approached accurately. Examples of copying the dynamics of an artificial neural network, the Lorenz system, and a variable star are given. Our idea paves a possible way towards copy a living brain.

Hong Zhao

Though the deep learning is pushing the machine learning to a new stage, basic theories of machine learning are still limited. The principle of learning, the role of the a prior knowledge, the role of neuron bias, and the basis for choosing neural transfer function and cost function, etc., are still far from clear. In this paper, we present a general theoretical framework for machine learning. We classify the prior knowledge into common and problem-dependent parts, and consider that the aim of learning is to maximally incorporate them. The principle we suggested for maximizing the former is the design risk minimization principle, while the neural transfer function, the cost function, as well as pretreatment of samples, are endowed with the role for maximizing the latter. The role of the neuron bias is explained from a different angle. We develop a Monte Carlo algorithm to establish the input-output responses, and we control the input-output sensitivity of a learning machine by controlling that of individual neurons. Applications of function approaching and smoothing, pattern recognition and classification, are provided to illustrate how to train general learning machines based on our theory and algorithm. Our method may in addition induce new applications, such as the transductive inference.

Rui Gao, Sergiy A. Vorobyov, Hong Zhao

The paper addresses the image fusion problem, where multiple images captured with different focus distances are to be combined into a higher quality all-in-focus image. Most current approaches for image fusion strongly rely on the unrealistic noise-free assumption used during the image acquisition, and then yield limited robustness in fusion processing. In our approach, we formulate the multi-focus image fusion problem in terms of an analysis sparse model, and simultaneously perform the restoration and fusion of multi-focus images. Based on this model, we propose an analysis operator learning, and define a novel fusion function to generate an all-in-focus image. Experimental evaluations confirm the effectiveness of the proposed fusion approach both visually and quantitatively, and show that our approach outperforms state-of-the-art fusion methods.

Hong Zhao

The support vector machine (SVM) is an important class of learning machines for function approach, pattern recognition, and time-serious prediction, etc. It maps samples into the feature space by so-called support vectors of selected samples, and then feature vectors are separated by maximum margin hyperplane. The present paper presents the general vector machine (GVM) to replace the SVM. The support vectors are replaced by general project vectors selected from the usual vector space, and a Monte Carlo (MC) algorithm is developed to find the general vectors. The general project vectors improves the feature-extraction ability, and the MC algorithm can control the width of the separation margin of the hyperplane. By controlling the separation margin, we show that the maximum margin hyperplane can usually induce the overlearning, and the best learning machine is achieved with a proper separation margin. Applications in function approach, pattern recognition, and classification indicate that the developed method is very successful, particularly for small-set training problems. Additionally, our algorithm may induce some particular applications, such as for the transductive inference.

Hong Zhao, Yifan Chen, Rui Wang et al.

Audio splicing is one of the most common manipulation techniques in the area of audio forensics. In this paper, the magnitudes of acoustic channel impulse response and ambient noise are proposed as the environmental signature. Specifically, the spliced audio segments are detected according to the magnitude correlation between the query frames and reference frames via a statically optimal threshold. The detection accuracy is further refined by comparing the adjacent frames. The effectiveness of the proposed method is tested on two data sets. One is generated from TIMIT database, and the other one is made in four acoustic environments using a commercial grade microphones. Experimental results show that the proposed method not only detects the presence of spliced frames, but also localizes the forgery segments with near perfect accuracy. Comparison results illustrate that the identification accuracy of the proposed scheme is higher than the previous schemes. In addition, experimental results also show that the proposed scheme is robust to MP3 compression attack, which is also superior to the previous works.

Bin Yang, Hong Zhao, William Zhu

The introduction of covering-based rough sets has made a substantial contribution to the classical rough sets. However, many vital problems in rough sets, including attribution reduction, are NP-hard and therefore the algorithms for solving them are usually greedy. Matroid, as a generalization of linear independence in vector spaces, it has a variety of applications in many fields such as algorithm design and combinatorial optimization. An excellent introduction to the topic of rough matroids is due to Zhu and Wang. On the basis of their work, we study the rough matroids based on coverings in this paper. First, we investigate some properties of the definable sets with respect to a covering. Specifically, it is interesting that the set of all definable sets with respect to a covering, equipped with the binary relation of inclusion $\subseteq$, constructs a lattice. Second, we propose the rough matroids based on coverings, which are a generalization of the rough matroids based on relations. Finally, some properties of rough matroids based on coverings are explored. Moreover, an equivalent formulation of rough matroids based on coverings is presented. These interesting and important results exhibit many potential connections between rough sets and matroids.

Hong Zhao, Fan Min, William Zhu

The measurement error with normal distribution is universal in applications. Generally, smaller measurement error requires better instrument and higher test cost. In decision making based on attribute values of objects, we shall select an attribute subset with appropriate measurement error to minimize the total test cost. Recently, error-range-based covering rough set with uniform distribution error was proposed to investigate this issue. However, the measurement errors satisfy normal distribution instead of uniform distribution which is rather simple for most applications. In this paper, we introduce normal distribution measurement errors to covering-based rough set model, and deal with test-cost-sensitive attribute reduction problem in this new model. The major contributions of this paper are four-fold. First, we build a new data model based on normal distribution measurement errors. With the new data model, the error range is an ellipse in a two-dimension space. Second, the covering-based rough set with normal distribution measurement errors is constructed through the "3-sigma" rule. Third, the test-cost-sensitive attribute reduction problem is redefined on this covering-based rough set. Fourth, a heuristic algorithm is proposed to deal with this problem. The algorithm is tested on ten UCI (University of California - Irvine) datasets. The experimental results show that the algorithm is more effective and efficient than the existing one. This study is a step toward realistic applications of cost-sensitive learning.