arXiv subjects

Cheng Xue

Publications and source records attributed to Cheng Xue.

51 records · Page 3Linked to original sources

arXiv2022

Don't do it: Safer Reinforcement Learning With Rule-based Guidance

During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dangerous and cause harm to their surroundings. Often, dangerous situations can be mitigated by defining a set of rules that the system should not violate under any conditions. For example, in robot navigation, one safety rule would be to avoid colliding with surrounding objects and people. In this work, we define safety rules in terms of the relationships between the agent and objects and use them to prevent reinforcement learning systems from performing potentially harmful actions. We propose a new safe epsilon-greedy algorithm that uses safety rules to override agents' actions if they are considered to be unsafe. In our experiments, we show that a safe epsilon-greedy policy significantly increases the safety of the agent during training, improves the learning efficiency resulting in much faster convergence, and achieves better performance than the base model.

cs.AI↗

arXiv2022

Quantum Algorithm for Solving a Quadratic Nonlinear System of Equations

Solving a quadratic nonlinear system of equations (QNSE) is a fundamental, but important, task in nonlinear science. We propose an efficient quantum algorithm for solving $n$-dimensional QNSE. Our algorithm embeds QNSE into a finite-dimensional system of linear equations using the homotopy perturbation method and a linearization technique; then we solve the linear equations with a quantum linear system solver and obtain a state which is $ε$-close to the normalized exact solution of the QNSE with success probability $Ω(1)$. The complexity of our algorithm is $O({\rm polylog}(n/ε))$, which provides an exponential improvement over the optimal classical algorithm in dimension $n$, and the dependence on $ε$ is almost optimal. Therefore, our algorithm exponentially accelerates the solution of QNSE and has wide applications in all kinds of nonlinear problems, contributing to the research progress of nonlinear science.

quant-ph↗

arXiv2022

Measuring Difficulty of Novelty Reaction

Current AI systems are designed to solve close-world problems with the assumption that the underlying world is remaining more or less the same. However, when dealing with real-world problems such assumptions can be invalid as sudden and unexpected changes can occur. To effectively deploy AI-powered systems in the real world, AI systems should be able to deal with open-world novelty quickly. Inevitably, dealing with open-world novelty raises an important question of novelty difficulty. Knowing whether one novelty is harder to deal with than another, can help researchers to train their systems systematically. In addition, it can also serve as a measurement of the performance of novelty robust AI systems. In this paper, we propose to define the novelty reaction difficulty as a relative difficulty of performing the known task after the introduction of the novelty. We propose a universal method that can be applied to approximate the difficulty. We present the approximations of the difficulty using our method and show how it aligns with the results of the evaluation of AI agents designed to deal with novelty.

cs.AI↗

arXiv2022

Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training

Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some noisy-labeled images, the network training procedure would suffer from difficulties, leading to a sub-optimal classifier. This problem is even more severe in the medical image analysis field, as the annotation quality of medical images heavily relies on the expertise and experience of annotators. In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high quality annotated medical data. Specifically, we employ the self-ensemble model with a noisy label filter to efficiently select the clean and noisy samples. Then, the clean samples are trained by a collaborative training strategy to eliminate the disturbance from imperfect labeled samples. Notably, we further design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples in a self-supervised manner. We evaluated our proposed robust learning strategy on four public medical image classification datasets with three types of label noise,ie,random noise, computer-generated label noise, and inter-observer variability noise. Our method outperforms other learning from noisy label methods and we also conducted extensive experiments to analyze each component of our method.

eess.IV↗

arXiv2021

Quantum homotopy perturbation method for nonlinear dissipative ordinary differential equations

While quantum computing provides an exponential advantage in solving linear differential equations, there are relatively few quantum algorithms for solving nonlinear differential equations. In our work, based on the homotopy perturbation method, we propose a quantum algorithm for solving $n$-dimensional nonlinear dissipative ordinary differential equations (ODEs). Our algorithm first converts the original nonlinear ODEs into the other nonlinear ODEs which can be embedded into finite-dimensional linear ODEs. Then we solve the embedded linear ODEs with quantum linear ODEs algorithm and obtain a state $ε$-close to the normalized exact solution of the original nonlinear ODEs with success probability $Ω(1)$. The complexity of our algorithm is $O(gηT{\rm poly}(\log(nT/ε)))$, where $η$, $g$ measure the decay of the solution. Our algorithm provides exponential improvement over the best classical algorithms or previous quantum algorithms in $n$ or $ε$.

quant-ph↗

arXiv2021

Quantum Newton's method for solving system of nonlinear algebraic equations

While quantum computing provides an exponential advantage in solving system of linear equations, there is little work to solve system of nonlinear equations with quantum computing. We propose quantum Newton's method (QNM) for solving $N$-dimensional system of nonlinear equations based on Newton's method. In QNM, we solve the system of linear equations in each iteration of Newton's method with quantum linear system solver. We use a specific quantum data structure and $l_{\infty}$ tomography with sample error $ε_s$ to implement the classical-quantum data conversion process between the two iterations of QNM, thereby constructing the whole process of QNM. The complexity of QNM in each iteration is $O(\log^4N/ε_s^2)$. Through numerical simulation, we find that when $ε_s>>1/\sqrt{N}$, QNM is still effective, so the complexity of QNM is sublinear with $N$, which provides quantum advantage compared with the optimal classical algorithm.

quant-ph↗

arXiv2021

Hi-Phy: A Benchmark for Hierarchical Physical Reasoning

Reasoning about the behaviour of physical objects is a key capability of agents operating in physical worlds. Humans are very experienced in physical reasoning while it remains a major challenge for AI. To facilitate research addressing this problem, several benchmarks have been proposed recently. However, these benchmarks do not enable us to measure an agent's granular physical reasoning capabilities when solving a complex reasoning task. In this paper, we propose a new benchmark for physical reasoning that allows us to test individual physical reasoning capabilities. Inspired by how humans acquire these capabilities, we propose a general hierarchy of physical reasoning capabilities with increasing complexity. Our benchmark tests capabilities according to this hierarchy through generated physical reasoning tasks in the video game Angry Birds. This benchmark enables us to conduct a comprehensive agent evaluation by measuring the agent's granular physical reasoning capabilities. We conduct an evaluation with human players, learning agents, and heuristic agents and determine their capabilities. Our evaluation shows that learning agents, with good local generalization ability, still struggle to learn the underlying physical reasoning capabilities and perform worse than current state-of-the-art heuristic agents and humans. We believe that this benchmark will encourage researchers to develop intelligent agents with advanced, human-like physical reasoning capabilities. URL: https://github.com/Cheng-Xue/Hi-Phy

cs.AI↗

arXiv2021

Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation

The superior performance of CNN on medical image analysis heavily depends on the annotation quality, such as the number of labeled image, the source of image, and the expert experience. The annotation requires great expertise and labour. To deal with the high inter-rater variability, the study of imperfect label has great significance in medical image segmentation tasks. In this paper, we present a novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation. Our model consists of three independent network, which can effectively learn useful information from the peer networks. The framework includes two stages. In the first stage, we select the clean annotated samples via a model committee setting, the networks are trained by minimizing a segmentation loss using the selected clean samples. In the second stage, we design a joint optimization framework with label correction to gradually correct the wrong annotation and improve the network performance. We conduct experiments on the public chest X-ray image datasets collected by Shenzhen Hospital. The results show that our methods could achieve a significant improvement on the accuracy in segmentation tasks compared to the previous methods.

eess.IV↗

arXiv2021

Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images

Automatic breast lesion segmentation in ultrasound helps to diagnose breast cancer, which is one of the dreadful diseases that affect women globally. Segmenting breast regions accurately from ultrasound image is a challenging task due to the inherent speckle artifacts, blurry breast lesion boundaries, and inhomogeneous intensity distributions inside the breast lesion regions. Recently, convolutional neural networks (CNNs) have demonstrated remarkable results in medical image segmentation tasks. However, the convolutional operations in a CNN often focus on local regions, which suffer from limited capabilities in capturing long-range dependencies of the input ultrasound image, resulting in degraded breast lesion segmentation accuracy. In this paper, we develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection (BD) modules for boosting the breast ultrasound lesion segmentation. The GGB utilizes the multi-layer integrated feature map as a guidance information to learn the long-range non-local dependencies from both spatial and channel domains. The BD modules learn additional breast lesion boundary map to enhance the boundary quality of a segmentation result refinement. Experimental results on a public dataset and a collected dataset show that our network outperforms other medical image segmentation methods and the recent semantic segmentation methods on breast ultrasound lesion segmentation. Moreover, we also show the application of our network on the ultrasound prostate segmentation, in which our method better identifies prostate regions than state-of-the-art networks.

eess.IV↗

arXiv2021

Quantum Finite Volume Method for Computational Fluid Dynamics with Classical Input and Output

Computational fluid dynamics (CFD) is a branch of fluid mechanics that uses numerical methods to solve fluid flows. The finite volume method (FVM) is an important one. In FVM, space is discretized to many grid cells. When the number of grid cells grows, massive computing resources are needed correspondingly. Recently, quantum computing has been proven to outperform a classical computer on specific computational tasks. However, the quantum CFD (QCFD) solver remains a challenge because the conversion between the classical and quantum data would become the bottleneck for the time complexity. Here we propose a QCFD solver with exponential speedup over classical counterparts and focus on how a quantum computer handles classical input and output. By utilizing quantum random access memory, the algorithm realizes sublinear time at every iteration step. The QCFD solver could allow new frontiers in the CFD area by allowing a finer mesh and faster calculation.

quant-ph↗

arXiv2019

Effects of Quantum Noise on Quantum Approximate Optimization Algorithm

The quantum-classical hybrid algorithm is an algorithm that holds promise in demonstrating the quantum advantage in NISQ devices. When running such algorithms, effects from quantum noise are inevitable. In our work, we consider a well-known hybrid algorithm, the quantum approximate optimization algorithm (QAOA). We study the effects on QAOA from typical quantum noise channels and produce several numerical results. Our research indicates that the output state fidelity, the cost function, and its gradient obtained from QAOA decrease exponentially with respect to the number of gates and noise strength. Moreover, we find that noise merely flattens the parameter space without changing its structure, so optimized parameters will not deviate from their ideal values. Our result provides evidence for the effectiveness of hybrid algorithms running on NISQ devices.

quant-ph↗

arXiv2019

An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis

Automated skin lesion analysis is very crucial in clinical practice, as skin cancer is among the most common human malignancy. Existing approaches with deep learning have achieved remarkable performance on this challenging task, however, heavily relying on large-scale labelled datasets. In this paper, we present a novel active learning framework for cost-effective skin lesion analysis. The goal is to effectively select and utilize much fewer labelled samples, while the network can still achieve state-of-the-art performance. Our sample selection criteria complementarily consider both informativeness and representativeness, derived from decoupled aspects of measuring model certainty and covering sample diversity. To make wise use of the selected samples, we further design a simple yet effective strategy to aggregate intra-class images in pixel space, as a new form of data augmentation. We validate our proposed method on data of ISIC 2017 Skin Lesion Classification Challenge for two tasks. Using only up to 50% of samples, our approach can achieve state-of-the-art performances on both tasks, which are comparable or exceeding the accuracies with full-data training, and outperform other well-known active learning methods by a large margin.

cs.CV↗

arXiv2019

VQNet: Library for a Quantum-Classical Hybrid Neural Network

Deep learning is a modern approach to realize artificial intelligence. Many frameworks exist to implement the machine learning task; however, performance is limited by computing resources. Using a quantum computer to accelerate training is a promising approach. The variational quantum circuit (VQC) has gained a great deal of attention because it can be run on near-term quantum computers. In this paper, we establish a new framework that merges traditional machine learning tasks with the VQC. Users can implement a trainable quantum operation into a neural network. This framework enables the training of a quantum-classical hybrid task and may lead to a new area of quantum machine learning.

quant-ph↗

arXiv2019

Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification

Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training procedure will immediately encounter difficulties, leading to a suboptimal classifier. This problem is even more crucial in the medical field, given that the annotation quality requires great expertise. In this paper, we propose an effective iterative learning framework for noisy-labeled medical image classification, to combat the lacking of high quality annotated medical data. Specifically, an online uncertainty sample mining method is proposed to eliminate the disturbance from noisy-labeled images. Next, we design a sample re-weighting strategy to preserve the usefulness of correctly-labeled hard samples. Our proposed method is validated on skin lesion classification task, and achieved very promising results.

cs.CV↗

arXiv2018

64-Qubit Quantum Circuit Simulation

Classical simulations of quantum circuits are limited in both space and time when the qubit count is above 50, the realm where quantum supremacy reigns. However, recently, for the low depth circuit with more than 50 qubits, there are several methods of simulation proposed by teams at Google and IBM. Here, we present a scheme of simulation which can extract a large amount of measurement outcomes within a short time, achieving a 64-qubit simulation of a universal random circuit of depth 22 using a 128-node cluster, and 56- and 42-qubit circuits on a single PC. We also estimate that a 72-qubit circuit of depth 23 can be simulated in about 16 h on a supercomputer identical to that used by the IBM team. Moreover, the simulation processes are exceedingly separable, hence parallelizable, involving just a few inter-process communications. Our work enables simulating more qubits with less hardware burden and provides a new perspective for classical simulations.

quant-ph↗