arXiv subjects

Peng Zhou

Publications and source records attributed to Peng Zhou.

At least 127 records · Page 7Linked to original sources

arXiv2023

A Classical Architecture For Digital Quantum Computers

Scaling bottlenecks the making of digital quantum computers, posing challenges from both the quantum and the classical components. We present a classical architecture to cope with a comprehensive list of the latter challenges {\em all at once}, and implement it fully in an end-to-end system by integrating a multi-core RISC-V CPU with our in-house control electronics. Our architecture enables scalable, high-precision control of large quantum processors and accommodates evolving requirements of quantum hardware. A central feature is a microarchitecture executing quantum operations in parallel on arbitrary predefined qubit groups. Another key feature is a reconfigurable quantum instruction set that supports easy qubit re-grouping and instructions extensions. As a demonstration, we implement the widely-studied surface code quantum computing workflow, which is instructive for being demanding on both the controllers and the integrated classical computation. Our design, for the first time, reduces instruction issuing and transmission costs to constants, which do not scale with the number of qubits, without adding any overheads in decoding or dispatching. Rather than relying on specialized hardware for syndrome decoding, our system uses a dedicated multi-core CPU for both qubit control and classical computation, including syndrome decoding. This simplifies the system design and facilitates load-balancing between the quantum and classical components. We implement recent proposals as decoding firmware on a RISC-V system-on-chip (SoC) that parallelizes general inner decoders. By using our in-house Union-Find and PyMatching 2 implementations, we can achieve unprecedented decoding capabilities of up to distances 47 and 67 with the currently available SoCs, under realistic and optimistic assumptions of physical error rate $p=0.001 and p=0.0001, respectively, all in just 1 \textmu s.

quant-ph↗

arXiv2023

Insights into Software Development Approaches: Mining Q&A Repositories

Context: Software practitioners adopt approaches like DevOps, Scrum, and Waterfall for high-quality software development. However, limited research has been conducted on exploring software development approaches concerning practitioners discussions on Q&A forums. Objective: We conducted an empirical study to analyze developers discussions on Q&A forums to gain insights into software development approaches in practice. Method: We analyzed 13,903 developers posts across Stack Overflow (SO), Software Engineering Stack Exchange (SESE), and Project Management Stack Exchange (PMSE) forums. A mixed method approach, consisting of the topic modeling technique (i.e., Latent Dirichlet Allocation (LDA)) and qualitative analysis, is used to identify frequently discussed topics of software development approaches, trends (popular, difficult topics), and the challenges faced by practitioners in adopting different software development approaches. Findings: We identified 15 frequently mentioned software development approaches topics on Q&A sites and observed an increase in trends for the top-3 most difficult topics requiring more attention. Finally, our study identified 49 challenges faced by practitioners while deploying various software development approaches, and we subsequently created a thematic map to represent these findings. Conclusions: The study findings serve as a useful resource for practitioners to overcome challenges, stay informed about current trends, and ultimately improve the quality of software products they develop.

cs.SE↗

arXiv2023

Cascaded Logic Gates Based on High-Performance Ambipolar Dual-Gate WSe2 Thin Film Transistors

Ambipolar dual-gate transistors based on two-dimensional (2D) materials, such as graphene, carbon nanotubes, black phosphorus, and certain transition metal dichalcogenides (TMDs), enable reconfigurable logic circuits with suppressed off-state current. These circuits achieve the same logical output as CMOS with fewer transistors and offer greater flexibility in design. The primary challenge lies in the cascadability and power consumption of these logic gates with static CMOS-like connections. In this article, high-performance ambipolar dual-gate transistors based on tungsten diselenide (WSe2) are fabricated. A high on-off ratio of 10^8 and 10^6, a low off-state current of 100 to 300 fA, a negligible hysteresis, and an ideal subthreshold swing of 62 and 63 mV/dec are measured in the p- and n-type transport, respectively. For the first time, we demonstrate cascadable and cascaded logic gates using ambipolar TMD transistors with minimal static power consumption, including inverters, XOR, NAND, NOR, and buffers made by cascaded inverters. A thorough study of both the control gate and polarity gate behavior is conducted, which has previously been lacking. The noise margin of the logic gates is measured and analyzed. The large noise margin enables the implementation of VT-drop circuits, a type of logic with reduced transistor number and simplified circuit design. Finally, the speed performance of the VT-drop and other circuits built by dual-gate devices are qualitatively analyzed. This work lays the foundation for future developments in the field of ambipolar dual-gate TMD transistors, showing their potential for low-power, high-speed and more flexible logic circuits.

cond-mat.mtrl-sci↗

arXiv2023

Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning

The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the discrepancy between classes of different tasks is not well learned (i.e., inter-task confusion, ITC), and certain priority is still given to the latest class batch (i.e., old-new confusion, ONC). We empirically validate the side effects of the two types of confusion. Meanwhile, a novel solution called Task Correlated Incremental Learning (TCIL) is proposed to encourage discriminative and fair feature utilization across tasks. TCIL performs a multi-level knowledge distillation to propagate knowledge learned from old tasks to the new one. It establishes information flow paths at both feature and logit levels, enabling the learning to be aware of old classes. Besides, attention mechanism and classifier re-scoring are applied to generate more fair classification scores. We conduct extensive experiments on CIFAR100 and ImageNet100 datasets. The results demonstrate that TCIL consistently achieves state-of-the-art accuracy. It mitigates both ITC and ONC, while showing advantages in battle with catastrophic forgetting even no rehearsal memory is reserved.

cs.CV↗

arXiv2022

Passive frustrated nanomagnet reservoir computing

Reservoir computing (RC) has received recent interest because reservoir weights do not need to be trained, enabling extremely low-resource consumption implementations, which could have a transformative impact on edge computing and in-situ learning where resources are severely constrained. Ideally, a natural hardware reservoir should be passive, minimal, expressive, and feasible; to date, proposed hardware reservoirs have had difficulty meeting all of these criteria. We therefore propose a reservoir that meets all of these criteria by leveraging the passive interactions of dipole-coupled, frustrated nanomagnets. The frustration significantly increases the number of stable reservoir states, enriching reservoir dynamics, and as such these frustrated nanomagnets fulfill all of the criteria for a natural hardware reservoir. We likewise propose a complete frustrated nanomagnet reservoir computing (NMRC) system with low-power complementary metal-oxide semiconductor (CMOS) circuitry to interface with the reservoir, and initial experimental results demonstrate the reservoir's feasibility. The reservoir is verified with micromagnetic simulations on three separate tasks demonstrating expressivity. The proposed system is compared with a CMOS echo-state-network (ESN), demonstrating an overall resource decrease by a factor of over 10,000,000, demonstrating that because NMRC is naturally passive and minimal it has the potential to be extremely resource efficient.

cs.NE↗

arXiv2022

A Dual-Arm Collaborative Framework for Dexterous Manipulation in Unstructured Environments with Contrastive Planning

Most object manipulation strategies for robots are based on the assumption that the object is rigid (i.e., with fixed geometry) and the goal's details have been fully specified (e.g., the exact target pose). However, there are many tasks that involve spatial relations in human environments where these conditions may be hard to satisfy, e.g., bending and placing a cable inside an unknown container. To develop advanced robotic manipulation capabilities in unstructured environments that avoid these assumptions, we propose a novel long-horizon framework that exploits contrastive planning in finding promising collaborative actions. Using simulation data collected by random actions, we learn an embedding model in a contrastive manner that encodes the spatio-temporal information from successful experiences, which facilitates the subgoal planning through clustering in the latent space. Based on the keypoint correspondence-based action parameterization, we design a leader-follower control scheme for the collaboration between dual arms. All models of our policy are automatically trained in simulation and can be directly transferred to real-world environments. To validate the proposed framework, we conduct a detailed experimental study on a complex scenario subject to environmental and reachability constraints in both simulation and real environments.

cs.RO↗

arXiv2022

WE model: A Machine Learning Model Based on Data-Driven Movie Derivatives Market Prediction

The mature development and the extension of the industry chain make the income structure of the film industry. The income of the traditional film industry depends on the box office and also includes movie merchandising, advertisement, home entertainment, book sales etc. Movie merchandising can even become more profitable than the box office. Therefore, market analysis and forecasting methods for multi-feature merchandising of multi-type films are particularly important. Traditional market research is time-consuming and labour-intensive, and its practical value is restricted. Due to the limited research method, more effective predictive analysis technology needs to be formed. With the rapid development of machine learning and big data, a large number of machine learning algorithms for predictive regression and classification recognition have been proposed and widely used in product design and industry analysis. This paper proposes a high-precision movie merchandising prediction model based on machine learning technology: WE model. This model integrates three machine learning algorithms to accurately predict the movie merchandising market. The WE model learns the relationship between the movie merchandising market and movie features by analyzing the main feature information of movies. After testing, the accuracy rate of prediction and evaluation in the merchandising market reaches 72.5%, and it has achieved a strong market control effect.

cs.CY↗

arXiv2022

A Multi-Sensor Interface to Improve the Learning Experience in Arc Welding Training Tasks

This paper presents the development of a multi-sensor user interface to facilitate the instruction of arc welding tasks. Traditional methods to acquire hand-eye coordination skills are typically conducted through one-to-one instruction where trainees must wear protective helmets and conduct several tests. This approach is inefficient as the harmful light emitted from the electric arc impedes the close monitoring of the process; Practitioners can only observe a small bright spot. To tackle these problems, recent training approaches have leveraged virtual reality to safely simulate the process and visualize the geometry of the workpieces. However, the synthetic nature of these types of simulation platforms reduces their effectiveness as they fail to comprise actual welding interactions with the environment, which hinders the trainees' learning process. To provide users with a real welding experience, we have developed a new multi-sensor extended reality platform for arc welding training. Our system is composed of: (1) An HDR camera, monitoring the real welding spot in real-time; (2) A depth sensor, capturing the 3D geometry of the scene; and (3) A head-mounted VR display, visualizing the process safely. Our innovative platform provides users with a "bot trainer", virtual cues of the seam geometry, automatic spot tracking, and performance scores. To validate the platform's feasibility, we conduct extensive experiments with several welding training tasks. We show that compared with the traditional training practice and recent virtual reality approaches, our automated multi-sensor method achieves better performances in terms of accuracy, learning curve, and effectiveness.

cs.HC↗

arXiv2022

Gradient-based Neuromorphic Learning on Dynamical RRAM Arrays

We present MEMprop, the adoption of gradient-based learning to train fully memristive spiking neural networks (MSNNs). Our approach harnesses intrinsic device dynamics to trigger naturally arising voltage spikes. These spikes emitted by memristive dynamics are analog in nature, and thus fully differentiable, which eliminates the need for surrogate gradient methods that are prevalent in the spiking neural network (SNN) literature. Memristive neural networks typically either integrate memristors as synapses that map offline-trained networks, or otherwise rely on associative learning mechanisms to train networks of memristive neurons. We instead apply the backpropagation through time (BPTT) training algorithm directly on analog SPICE models of memristive neurons and synapses. Our implementation is fully memristive, in that synaptic weights and spiking neurons are both integrated on resistive RAM (RRAM) arrays without the need for additional circuits to implement spiking dynamics, e.g., analog-to-digital converters (ADCs) or thresholded comparators. As a result, higher-order electrophysical effects are fully exploited to use the state-driven dynamics of memristive neurons at run time. By moving towards non-approximate gradient-based learning, we obtain highly competitive accuracy amongst previously reported lightweight dense fully MSNNs on several benchmarks.

cs.NE↗

arXiv2022

Model Predictive Manipulation of Compliant Objects with Multi-Objective Optimizer and Adversarial Network for Occlusion Compensation

The robotic manipulation of compliant objects is currently one of the most active problems in robotics due to its potential to automate many important applications. Despite the progress achieved by the robotics community in recent years, the 3D shaping of these types of materials remains an open research problem. In this paper, we propose a new vision-based controller to automatically regulate the shape of compliant objects with robotic arms. Our method uses an efficient online surface/curve fitting algorithm that quantifies the object's geometry with a compact vector of features; This feedback-like vector enables to establish an explicit shape servo-loop. To coordinate the motion of the robot with the computed shape features, we propose a receding-time estimator that approximates the system's sensorimotor model while satisfying various performance criteria. A deep adversarial network is developed to robustly compensate for visual occlusions in the camera's field of view, which enables to guide the shaping task even with partial observations of the object. Model predictive control is utilized to compute the robot's shaping motions subject to workspace and saturation constraints. A detailed experimental study is presented to validate the effectiveness of the proposed control framework.

cs.RO↗

arXiv2022

Logical and Physical Reversibility of Conservative Skyrmion Logic

Magnetic skyrmions are nanoscale whirls of magnetism that can be propagated with electrical currents. The repulsion between skyrmions inspires their use for reversible computing based on the elastic billiard ball collisions proposed for conservative logic in 1982. Here we evaluate the logical and physical reversibility of this skyrmion logic paradigm, as well as the limitations that must be addressed before dissipation-free computation can be realized.

cs.ET↗

arXiv2022

A Fully Memristive Spiking Neural Network with Unsupervised Learning

We present a fully memristive spiking neural network (MSNN) consisting of physically-realizable memristive neurons and memristive synapses to implement an unsupervised Spiking Time Dependent Plasticity (STDP) learning rule. The system is fully memristive in that both neuronal and synaptic dynamics can be realized by using memristors. The neuron is implemented using the SPICE-level memristive integrate-and-fire (MIF) model, which consists of a minimal number of circuit elements necessary to achieve distinct depolarization, hyperpolarization, and repolarization voltage waveforms. The proposed MSNN uniquely implements STDP learning by using cumulative weight changes in memristive synapses from the voltage waveform changes across the synapses, which arise from the presynaptic and postsynaptic spiking voltage signals during the training process. Two types of MSNN architectures are investigated: 1) a biologically plausible memory retrieval system, and 2) a multi-class classification system. Our circuit simulation results verify the MSNN's unsupervised learning efficacy by replicating biological memory retrieval mechanisms, and achieving 97.5% accuracy in a 4-pattern recognition problem in a large scale discriminative MSNN.

cs.NE↗

arXiv2022

SPICEprop: Backpropagating Errors Through Memristive Spiking Neural Networks

We present a fully memristive spiking neural network (MSNN) consisting of novel memristive neurons trained using the backpropagation through time (BPTT) learning rule. Gradient descent is applied directly to the memristive integrated-and-fire (MIF) neuron designed using analog SPICE circuit models, which generates distinct depolarization, hyperpolarization, and repolarization voltage waveforms. Synaptic weights are trained by BPTT using the membrane potential of the MIF neuron model and can be processed on memristive crossbars. The natural spiking dynamics of the MIF neuron model are fully differentiable, eliminating the need for gradient approximations that are prevalent in the spiking neural network literature. Despite the added complexity of training directly on SPICE circuit models, we achieve 97.58% accuracy on the MNIST testing dataset and 75.26% on the Fashion-MNIST testing dataset, the highest accuracies among all fully MSNNs.

cs.NE↗

arXiv2021

Synchronous Unsupervised STDP Learning with Stochastic STT-MRAM Switching

The use of analog resistance states for storing weights in neuromorphic systems is impeded by fabrication imprecision and device stochasticity that limit the precision of synapse weights. This challenge can be resolved by emulating analog behavior with the stochastic switching of the binary states of spin-transfer torque magnetoresistive random-access memory (STT-MRAM). However, previous approaches based on STT-MRAM operate in an asynchronous manner that is difficult to implement experimentally. This paper proposes a synchronous spiking neural network system with clocked circuits that perform unsupervised learning leveraging the stochastic switching of STT-MRAM. The proposed system enables a single-layer network to achieve 90% inference accuracy on the MNIST dataset.

cs.NE↗

arXiv2021

Experimental Demonstration of Neuromorphic Network with STT MTJ Synapses

We present the first experimental demonstration of a neuromorphic network with magnetic tunnel junction (MTJ) synapses, which performs image recognition via vector-matrix multiplication. We also simulate a large MTJ network performing MNIST handwritten digit recognition, demonstrating that MTJ crossbars can match memristor accuracy while providing increased precision, stability, and endurance.

cs.NE↗

arXiv2021

An Improved Reinforcement Learning Model Based on Sentiment Analysis

With the development of artificial intelligence technology, quantitative trading systems represented by reinforcement learning have emerged in the stock trading market. The authors combined the deep Q network in reinforcement learning with the sentiment quantitative indicator ARBR to build a high-frequency stock trading model for the share market. To improve the performance of the model, the PCA algorithm is used to reduce the dimensionality feature vector while incorporating the influence of market sentiment on the long-short power into the spatial state of the trading model and uses the LSTM layer to replace the fully connected layer to solve the traditional DQN model due to limited empirical data storage. Through the use of cumulative income, Sharpe ratio to evaluate the performance of the model and the use of double moving averages and other strategies for comparison. The results show that the improved model proposed by authors is far superior to the comparison model in terms of income, achieving a maximum annualized rate of return of 54.5%, which is proven to be able to increase reinforcement learning performance significantly in stock trading.

q-fin.ST↗

arXiv2021

Prediction of Fund Net Value Based on ARIMA-LSTM Hybrid Model

The net value of the fund is affected by performance and market, and the researchers try to quantify these effects to predict the future net value by establishing different models. The current prediction models usually can only reflect the linear variation law, poorly handled or selectively ignore their nonlinear characteristics, so the prediction results are usually less accurate. This paper uses a fund prediction method based on the ARIMA-LSTM hybrid model. After preprocessing the historical data, the first filter out the linear data characteristics with the ARIMA model, then pass the data to the LSTM model to extract the nonlinear characteristic by residual, and finally superposition the respective prediction values of the two models to obtain the prediction results of the hybrid model. Empirically shows that the methods in the paper are more accurate and applicable than traditional fund prediction methods.

q-fin.ST↗

arXiv2021

Improved Method of Stock Trading under Reinforcement Learning Based on DRQN and Sentiment Indicators ARBR

With the application of artificial intelligence in the financial field, quantitative trading is considered to be profitable. Based on this, this paper proposes an improved deep recurrent DRQN-ARBR model because the existing quantitative trading model ignores the impact of irrational investor behavior on the market, making the application effect poor in an environment where the stock market in China is non-efficiency. By changing the fully connected layer in the original model to the LSTM layer and using the emotion indicator ARBR to construct a trading strategy, this model solves the problems of the traditional DQN model with limited memory for empirical data storage and the impact of observable Markov properties on performance. At the same time, this paper also improved the shortcomings of the original model with fewer stock states and chose more technical indicators as the input values of the model. The experimental results show that the DRQN-ARBR algorithm proposed in this paper can significantly improve the performance of reinforcement learning in stock trading.

q-fin.ST↗