检索结果-内蒙古大学图书馆

Improving Zero-Shot Coordination with Diversely Rewarded Partner Agents

学校读者我要写书评

暂无评论

Improving Zero-Shot Coordination with Diversely Rewarded Par...

International Joint Conference on Neural Networks (IJCNN)

作者： Peilin Wu Zhenhua Yang Peng Yang Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Statistics and Data Science Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Zero-shot coordination studies the training of well-generalizing human-AI coordination agents in the scenario where human data is unavailable. To obtain a coordination agent generalize to unseen humans, prevailing methods generate a population of partner agents as proxy models of human partners and then train a coordination agent with these partner agents. Constructed partner agents are expected to be as diverse as possible to cover a wide range of human behaviors, preventing a distribution shift between training and testing stages. Recent works concentrate on studying effective methods of creating a group of high-reward while diverse partner agents to model unseen human partners. However, the resulting high-reward partner agents do not accurately reflect real-world situations, considering that human decisions are not always optimal and may sometimes even hinder the progression of coordination. Therefore, these studies still struggle to capture the potential characteristics of human partners. In this work, reinforcement learning (RL) and supervised learning (SL) are integrated to train a reward-conditioned policy. By conditioned on different desired rewards, a reward-conditioned policy simulates both low-reward and high-reward partners. Additionally, a reward-bucketed replay buffer and curriculum learning are applied to enhance reward diversity and boost the training of coordination agents. Experiments demonstrate that the proposed reward-conditioned policy is capable of generating agents with different rewards. Moreover, the zero-shot coordination performance of agents trained with these partners surpasses previous methods in the majority of scenarios within the Overcooked human-AI coordination benchmark.

关键词： Training Impedance matching Supervised learning Neural networks Reinforcement learning Benchmark testing Trajectory

An EEG-based intelligent Neuromarketing System for Predicting Consumers’ Choice 4th

学校读者我要写书评

暂无评论

An EEG-based Intelligent Neuromarketing System for Predicti...

International Conference on 4th Industrial Revolution and Beyond, IC4IR 2021

作者： Mashrur, Fazla Rabbi Rahman, Khandoker Mahmudur Miya, Mohammad Tohidul Islam Vaidyanathan, Ravi Anwar, Syed Ferhat Sarker, Farhana Mamun, Khondaker A. Advanced Intelligent Multidisciplinary Systems Lab Institute of Advanced Research United International University Dhaka Bangladesh School of Business and Economics United International University Dhaka Bangladesh Department of Mechanical Engineering Imperial College London London United Kingdom Institute of Business Administration University of Dhaka Dhaka Bangladesh Department of Computer Science and Engineering University of Liberal Arts Bangladesh Dhaka Bangladesh

ISBN: (纸本)9789811980312

Marketers use different marketing strategies to elicit the desired response from the target customers. To measure customer engagement, they usually conduct one-on-one interviews, surveys, broad polls, and focus group discussions. However, these are costly and sometimes unreliable. On the other hand, neuromarketing measures customer response to marketing stimuli by measuring the electrical activity of the brain and has the potential to address these drawbacks. which can be overcome by neuromarketing. In this work, we proposed a prediction algorithm that can identify consumer affective attitude (AA) and purchase intention (PI) from EEG signals from the brain. At first, the raw EEG signals are initially preprocessed to remove noise. After that, three features are extracted: time, frequency, and time frequency domain features. Wavelet packet transform is used to separate the EEG bands in time-domain feature extraction. Then, for feature selection, wrapper-based SVM-RFE is utilized. Finally, we use SVM to distinguish the classes in AA and PI. Results show that for SVM with radial basis function kernel performs better to classify positive and negative AA with an accuracy of 90 ± 4.33 and PI with an accuracy of 75 ± 2.5. So, EEG-based neuromarketing solutions can assist companies and organizations in accurately predicting future consumer preferences. As a result, neuromarketing based-solutions have the potential to increase sales by overcoming the constraints of traditional marketing. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electroencephalography

Message-Passing on Hypergraphs: Detectability, Phase Transitions and Higher-Order Information

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ruggeri, Nicolò Lonardi, Alessandro De Bacco, Caterina Max Planck Institute for Intelligent Systems Cyber Valley Tübingen72076 Germany Department of Computer Science ETH Zürich8004 Switzerland

Hypergraphs are widely adopted tools to examine systems with higher-order interactions. Despite recent advancements in methods for community detection in these systems, we still lack a theoretical analysis of their detectability limits. Here, we derive closed-form bounds for community detection in hypergraphs. Using a Message-Passing formulation, we demonstrate that detectability depends on hypergraphs’ structural properties, such as the distribution of hyperedge sizes or their assortativity. Our formulation enables a characterization of the entropy of a hypergraph in relation to that of its clique expansion, showing that community detection is enhanced when hyperedges highly overlap on pairs of nodes. We develop an efficient Message-Passing algorithm to learn communities and model parameters on large systems. Additionally, we devise an exact sampling routine to generate synthetic data from our probabilistic model. With these methods, we numerically investigate the boundaries of community detection in synthetic datasets, and extract communities from real systems. Our results extend the understanding of the limits of community detection in hypergraphs and introduce flexible mathematical tools to study systems with higher-order interactions. Copyright © 2023, The Authors. All rights reserved.

关键词： Message passing

Evolutionary Dynamic Optimization-Based Calibration Framework for Agent-Based Financial Market Simulators

学校读者我要写书评

暂无评论

Evolutionary Dynamic Optimization-Based Calibration Framewor...

Congress on Evolutionary Computation

作者： Zhenhua Yang Muyao Zhong Peng Yang Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Statistics and Data Science Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

The agent-based financial market simulators serve as an important validation tool for trading strategies. For high-fidelity simulation, it is pivotal to calibrate the parameters of a simulator so that the generated simulation data resembles the observed real market data of interest. In traditional calibration methods, it is typical that the parameters of the simulator are set to be time-invariant. However, the dynamic nature of the real financial market introduces various variability into the behaviors of the market participants over different time intervals, posing in-herent limitations to the traditional methods. A more reasonable approach might involve employing a simulator with time-variant parameters. This suggests that the model parameters can be dynamically adjusted at different stages of the simulation to adapt to the evolving market. Consequently, the calibration problem of the financial market simulators can be treated as a dynamic optimization problem. To dynamically calibrate the simulators, we introduce an Evolutionary Dynamic Optimization (EDO) framework. By monitoring the changes of the best fitness, the whole simulation time interval is adaptively divided into multiple stages. Then the Negatively Correlated Search (NCS) algorithm is employed to effectively adjust the parameters at different simulation stages to better simulate the real financial market. Empirical results on both synthetic and real data verify that our dynamic calibration framework significantly outperforms traditional calibration methods that fixing a parameter for the whole simulation interval. The proposed strategy of detecting dynamic changes is also shown to be more reliable than the naive method of manually segmenting stages. In terms of calibration time, our proposed method significantly improves by nearly 93% compared to the fixed parameter setting, and approximately 61% compared to manual segmentation calibration.

关键词： Adaptation models Fluctuations Heuristic algorithms Computational modeling Scalability Manuals Data models

Kronecker-factored approximate curvature for modern neural network architectures 23

学校读者我要写书评

暂无评论

Kronecker-factored approximate curvature for modern neural n...

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Runa Eschenhagen Alexander Immer Richard E. Turner Frank Schneider Philipp Hennig University of Cambridge Department of Computer Science ETH Zurich and Max Planck Institute for Intelligent Systems University of Tübingen and Tübingen AI Center

The core components of many modern neural network architectures, such as transformers, convolutional, or graph neural networks, can be expressed as linear layers with weight-sharing. Kronecker-Factored Approximate Curvature (K-FAC), a second-order optimisation method, has shown promise to speed up neural network training and thereby reduce computational costs. However, there is currently no framework to apply it to generic architectures, specifically ones with linear weight-sharing layers. In this work, we identify two different settings of linear weight-sharing layers which motivate two flavours of K-FAC - expand and reduce. We show that they are exact for deep linear networks with weight-sharing in their respective setting. Notably, K-FAC-reduce is generally faster than K-FAC-expand, which we leverage to speed up automatic hyperparameter selection via optimising the marginal likelihood for a Wide ResNet. Finally, we observe little difference between these two K-FAC variations when using them to train both a graph neural network and a vision transformer. However, both variations are able to reach a fixed validation metric target in 50-75% of the number of steps of a first-order reference run, which translates into a comparable improvement in wall-clock time. This highlights the potential of applying K-FAC to modern neural network architectures.

关键词：

Guideline for Trustworthy Artificial Intelligence - AI Assessment Catalog

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Poretschkin, Maximilian Houben, Sebastian Schmitz, Anna Mock, Michael Akila, Maram Rosenzweig, Julia Adilova, Linara Sicking, Joachim Becker, Daniel Schulz, Elena Cremers, Armin B. Voss, Angelika Hecker, Dirk Wrobel, Stefan Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Schloss Birlinghoven Sankt Augustin Germany Department of Computer Science University of Bonn Bonn Germany

Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. Prominent use cases include applications in medical diagnostics, predictive maintenance and, in the future, autonomous driving. However, it is clear that AI and business models based on it can only reach their full potential if AI applications are developed according to high quality standards and are effectively protected against new AI risks. For instance, AI bears the risk of unfair treatment of individuals when processing personal data e.g., to support credit lending or staff recruitment decisions. Serious false predictions resulting from minor disturbances in the input data are another example – for instance, when pedestrians are not detected by an autonomous vehicle due to image noise. The emergence of these new risks is closely linked to the fact that the process for developing AI applications, particularly those based on Machine Learning (ML), strongly differs from that of conventional software. This is because the behavior of AI applications is essentially learned from large volumes of data and is not predetermined by fixed programmed rules. Thus, the issue of the trustworthiness of AI applications is crucial and is the subject of numerous major publications by stakeholders in politics, business and society. Noteworthy mentions include the European Commission’s draft regulation, the AI Standardization Roadmap and the recommendations of the High-Level Expert Group on AI, which formulate essential guidelines for the trustworthy use of Artificial Intelligence. In addition to these resources, there is mutual agreement that the requirements for trustworthy AI, which are often described in an abstract way, must now be made clear and tangible. One challenge to overcome here relates to the fact that the specific quality criteria for an AI application depend heavily on the application context and possible meas

关键词： Quality control

Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Immer, Alexander van der Ouderaa, Tycho F.A. van der Wilk, Mark Rätsch, Gunnar Schölkopf, Bernhard Department of Computer Science ETH Zurich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany Imperial College London United Kingdom

Selecting hyperparameters in deep learning greatly impacts its effectiveness but requires manual effort and expertise. Recent works show that Bayesian model selection with Laplace approximations can allow to optimize such hyperparameters just like standard neural network parameters using gradients and on the training data. However, estimating a single hyperparameter gradient requires a pass through the entire dataset, limiting the scalability of such algorithms. In this work, we overcome this issue by introducing lower bounds to the linearized Laplace approximation of the marginal likelihood. In contrast to previous estimators, these bounds are amenable to stochastic-gradient-based optimization and allow to trade off estimation accuracy against computational complexity. We derive them using the function-space form of the linearized Laplace, which can be estimated using the neural tangent kernel. Experimentally, we show that the estimators can significantly accelerate gradient-based hyperparameter optimization. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

AG3D: Learning to Generate 3D Avatars from 2D Image Collections

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dong, Zijian Chen, Xu Yang, Jinlong Black, Michael J. Hilliges, Otmar Geiger, Andreas ETH Zürich Department of Computer Science Switzerland University of Tübingen Germany Max Planck Institute for Intelligent Systems Tübingen Germany

While progress in 2D generative models of human appearance has been rapid, many applications require 3D avatars that can be animated and rendered. Unfortunately, most existing methods for learning generative models of 3D humans with diverse shape and appearance require 3D training data, which is limited and expensive to acquire. The key to progress is hence to learn generative models of 3D avatars from abundant unstructured 2D image collections. However, learning realistic and complete 3D appearance and geometry in this under-constrained setting remains challenging, especially in the presence of loose clothing such as dresses. In this paper, we propose a new adversarial generative model of realistic 3D people from 2D images. Our method captures shape and deformation of the body and loose clothing by adopting a holistic 3D generator and integrating an efficient and flexible articulation module. To improve realism, we train our model using multiple discriminators while also integrating geometric cues in the form of predicted 2D normal maps. We experimentally find that our method outperforms previous 3D- and articulation-aware methods in terms of geometry and appearance. We validate the effectiveness of our model and the importance of each component via systematic ablation studies. © 2023, CC BY.

关键词： Geometry

Structure and inference in hypergraphs with node attributes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Badalyan, Anna Ruggeri, Nicolò De Bacco, Caterina Max Planck Institute for Intelligent Systems Cyber Valley Tübingen72076 Germany Department of Computer Science ETH Zürich8004 Switzerland

Many networked datasets with units interacting in groups of two or more, encoded with hypergraphs, are accompanied by extra information about nodes, such as the role of an individual in a workplace. Here we show how these node attributes can be used to improve our understanding of the structure resulting from higher-order interactions. We consider the problem of community detection in hypergraphs and develop a principled model that combines higher-order interactions and node attributes to better represent the observed interactions and to detect communities more accurately than using either of these types of information alone. The method learns automatically from the input data the extent to which structure and attributes contribute to explain the data, down weighing or discarding attributes if not informative. Our algorithmic implementation is efficient and scales to large hypergraphs and interactions of large numbers of units. We apply our method to a variety of systems, showing strong performance in hyperedge prediction tasks and in selecting community divisions that correlate with attributes when these are informative, but discarding them otherwise. Our approach illustrates the advantage of using informative node attributes when available with higher-order data. © 2023, CC BY-NC-SA.

关键词：