Paul D. Yoo

Jiaxian Guo, Bo Yang, Paul Yoo et al. · allen-ai, uw

Unlike perfect information games, where all elements are known to every player, imperfect information games emulate the real-world complexities of decision-making under uncertain or incomplete information. GPT-4, the recent breakthrough in large language models (LLMs) trained on massive passive data, is notable for its knowledge retrieval and reasoning abilities. This paper delves into the applicability of GPT-4's learned knowledge for imperfect information games. To achieve this, we introduce \textbf{Suspicion-Agent}, an innovative agent that leverages GPT-4's capabilities for performing in imperfect information games. With proper prompt engineering to achieve different functions, Suspicion-Agent based on GPT-4 demonstrates remarkable adaptability across a range of imperfect information card games. Importantly, GPT-4 displays a strong high-order theory of mind (ToM) capacity, meaning it can understand others and intentionally impact others' behavior. Leveraging this, we design a planning strategy that enables GPT-4 to competently play against different opponents, adapting its gameplay style as needed, while requiring only the game rules and descriptions of observations as input. In the experiments, we qualitatively showcase the capabilities of Suspicion-Agent across three different imperfect information games and then quantitatively evaluate it in Leduc Hold'em. The results show that Suspicion-Agent can potentially outperform traditional algorithms designed for imperfect information games, without any specialized training or examples. In order to encourage and foster deeper insights within the community, we make our game-related data publicly available.

Paul Yoo, Jiaxian Guo, Yutaka Matsuo et al. · uw

Synthesizing novel view images from a few views is a challenging but practical problem. Existing methods often struggle with producing high-quality results or necessitate per-object optimization in such few-view settings due to the insufficient information provided. In this work, we explore leveraging the strong 2D priors in pre-trained diffusion models for synthesizing novel view images. 2D diffusion models, nevertheless, lack 3D awareness, leading to distorted image synthesis and compromising the identity. To address these problems, we propose DreamSparse, a framework that enables the frozen pre-trained diffusion model to generate geometry and identity-consistent novel view image. Specifically, DreamSparse incorporates a geometry module designed to capture 3D features from sparse views as a 3D prior. Subsequently, a spatial guidance model is introduced to convert these 3D feature maps into spatial information for the generative process. This information is then used to guide the pre-trained diffusion model, enabling it to generate geometrically consistent images without tuning it. Leveraging the strong image priors in the pre-trained diffusion models, DreamSparse is capable of synthesizing high-quality novel views for both object and scene-level images and generalising to open-set images. Experimental results demonstrate that our framework can effectively synthesize novel view images from sparse views and outperforms baselines in both trained and open-set category images. More results can be found on our project page: https://sites.google.com/view/dreamsparse-webpage.

So Kuroki, Jiaxian Guo, Tatsuya Matsushima et al. · uw

Due to the inherent uncertainty in their deformability during motion, previous methods in deformable object manipulation, such as rope and cloth, often required hundreds of real-world demonstrations to train a manipulation policy for each object, which hinders their applications in our ever-changing world. To address this issue, we introduce GenDOM, a framework that allows the manipulation policy to handle different deformable objects with only a single real-world demonstration. To achieve this, we augment the policy by conditioning it on deformable object parameters and training it with a diverse range of simulated deformable objects so that the policy can adjust actions based on different object parameters. At the time of inference, given a new object, GenDOM can estimate the deformable object parameters with only a single real-world demonstration by minimizing the disparity between the grid density of point clouds of real-world demonstrations and simulations in a differentiable physics simulator. Empirical validations on both simulated and real-world object manipulation setups clearly show that our method can manipulate different objects with a single demonstration and significantly outperforms the baseline in both environments (a 62% improvement for in-domain ropes and a 15% improvement for out-of-distribution ropes in simulation, as well as a 26% improvement for ropes and a 50% improvement for cloths in the real world), demonstrating the effectiveness of our approach in one-shot deformable object manipulation.

So Kuroki, Jiaxian Guo, Tatsuya Matsushima et al. · uw

Due to the inherent uncertainty in their deformability during motion, previous methods in rope manipulation often require hundreds of real-world demonstrations to train a manipulation policy for each rope, even for simple tasks such as rope goal reaching, which hinder their applications in our ever-changing world. To address this issue, we introduce GenORM, a framework that allows the manipulation policy to handle different deformable ropes with a single real-world demonstration. To achieve this, we augment the policy by conditioning it on deformable rope parameters and training it with a diverse range of simulated deformable ropes so that the policy can adjust actions based on different rope parameters. At the time of inference, given a new rope, GenORM estimates the deformable rope parameters by minimizing the disparity between the grid density of point clouds of real-world demonstrations and simulations. With the help of a differentiable physics simulator, we require only a single real-world demonstration. Empirical validations on both simulated and real-world rope manipulation setups clearly show that our method can manipulate different ropes with a single demonstration and significantly outperforms the baseline in both environments (62% improvement in in-domain ropes, and 15% improvement in out-of-distribution ropes in simulation, 26% improvement in real-world), demonstrating the effectiveness of our approach in one-shot rope manipulation.

Stephanie Wenxin Liu, Michael Fischer, Paul D. Yoo et al.

Bounding volumes are an established concept in computer graphics and vision tasks but have seen little change since their early inception. In this work, we study the use of neural networks as bounding volumes. Our key observation is that bounding, which so far has primarily been considered a problem of computational geometry, can be redefined as a problem of learning to classify space into free or occupied. This learning-based approach is particularly advantageous in high-dimensional spaces, such as animated scenes with complex queries, where neural networks are known to excel. However, unlocking neural bounding requires a twist: allowing -- but also limiting -- false positives, while ensuring that the number of false negatives is strictly zero. We enable such tight and conservative results using a dynamically-weighted asymmetric loss function. Our results show that our neural bounding produces up to an order of magnitude fewer false positives than traditional methods. In addition, we propose an extension of our bounding method using early exits that accelerates query speeds by 25%. We also demonstrate that our approach is applicable to non-deep learning models that train within seconds. Our project page is at: https://wenxin-liu.github.io/neural_bounding/.

Kamal Taha, Paul D. Yoo, Chan Yeun et al.

The exponential growth of textual data presents substantial challenges in management and analysis, notably due to high storage and processing costs. Text classification, a vital aspect of text mining, provides robust solutions by enabling efficient categorization and organization of text data. These techniques allow individuals, researchers, and businesses to derive meaningful patterns and insights from large volumes of text. This survey paper introduces a comprehensive taxonomy specifically designed for text classification based on research fields. The taxonomy is structured into hierarchical levels: research field-based category, research field-based sub-category, methodology-based technique, methodology sub-technique, and research field applications. We employ a dual evaluation approach: empirical and experimental. Empirically, we assess text classification techniques across four critical criteria. Experimentally, we compare and rank the methodology sub-techniques within the same methodology technique and within the same overall research field sub-category. This structured taxonomy, coupled with thorough evaluations, provides a detailed and nuanced understanding of text classification algorithms and their applications, empowering researchers to make informed decisions based on precise, field-specific insights.

Kamal Taha, Paul D. Yoo, Aya Taha

This survey paper provides a comprehensive analysis of big data algorithms in recommendation systems, addressing the lack of depth and precision in existing literature. It proposes a two-pronged approach: a thorough analysis of current algorithms and a novel, hierarchical taxonomy for precise categorization. The taxonomy is based on a tri-level hierarchy, starting with the methodology category and narrowing down to specific techniques. Such a framework allows for a structured and comprehensive classification of algorithms, assisting researchers in understanding the interrelationships among diverse algorithms and techniques. Covering a wide range of algorithms, this taxonomy first categorizes algorithms into four main analysis types: User and Item Similarity-Based Methods, Hybrid and Combined Approaches, Deep Learning and Algorithmic Methods, and Mathematical Modeling Methods, with further subdivisions into sub-categories and techniques. The paper incorporates both empirical and experimental evaluations to differentiate between the techniques. The empirical evaluation ranks the techniques based on four criteria. The experimental assessments rank the algorithms that belong to the same category, sub-category, technique, and sub-technique. Also, the paper illuminates the future prospects of big data techniques in recommendation systems, underscoring potential advancements and opportunities for further research in this field

Song-Kyoo Kim, Chan Yeob Yeun, Paul D. Yoo et al.

Deep learning applied to electrocardiogram (ECG) data can be used to achieve personal authentication in biometric security applications, but it has not been widely used to diagnose cardiovascular disorders. We developed a deep learning model for the detection of arrhythmia in which time-sliced ECG data representing the distance between successive R-peaks are used as the input for a convolutional neural network (CNN). The main objective is developing the compact deep learning based detect system which minimally uses the dataset but delivers the confident accuracy rate of the Arrhythmia detection. This compact system can be implemented in wearable devices or real-time monitoring equipment because the feature extraction step is not required for complex ECG waveforms, only the R-peak data is needed. The results of both tests indicated that the Compact Arrhythmia Detection System (CADS) matched the performance of conventional systems for the detection of arrhythmia in two consecutive test runs. All features of the CADS are fully implemented and publicly available in MATLAB.

Amang Song-Kyoo Kim, Chan Yeob Yeun, Paul D. Yoo

This paper is targeted in the area of biometric data enabled security system based on the machine learning for the digital health. The disadvantages of traditional authentication systems include the risks of forgetfulness, loss, and theft. Biometric authentication is therefore rapidly replacing traditional authentication methods and is becoming an everyday part of life. The electrocardiogram (ECG) was recently introduced as a biometric authentication system suitable for security checks. The proposed authentication system helps investigators studying ECG-based biometric authentication techniques to reshape input data by slicing based on the RR-interval, and defines the Overall Performance (OP), which is the combined performance metric of multiple authentication measures. We evaluated the performance of the proposed system using a confusion matrix and achieved up to 95% accuracy by compact data analysis. We also used the Amang ECG (amgecg) toolbox in MATLAB to investigate the upper-range control limit (UCL) based on the mean square error, which directly affects three authentication performance metrics: the accuracy, the number of accepted samples, and the OP. Using this approach, we found that the OP can be optimized by using a UCL of 0.0028, which indicates 61 accepted samples out of 70 and ensures that the proposed authentication system achieves an accuracy of 95%.

Ebrahim Al Alkeem, Song-Kyoo Kim, Chan Yeob Yeun et al.

Traditional authentication systems use alphanumeric or graphical passwords, or token-based techniques that require "something you know and something you have". The disadvantages of these systems include the risks of forgetfulness, loss, and theft. To address these shortcomings, biometric authentication is rapidly replacing traditional authentication methods and is becoming a part of everyday life. The electrocardiogram (ECG) is one of the most recent traits considered for biometric purposes. In this work we describe an ECG-based authentication system suitable for security checks and hospital environments. The proposed system will help investigators studying ECG-based biometric authentication techniques to define dataset boundaries and to acquire high-quality training data. We evaluated the performance of the proposed system and found that it could achieve up to the 92 percent identification accuracy. In addition, by applying the Amang ECG (amgecg) toolbox within MATLAB, we investigated the two parameters that directly affect the accuracy of authentication: the ECG slicing time (sliding window) and the sampling time period, and found their optimal values.

O. Y. Al-Jarrah, P. D. Yoo, S Muhaidat et al.

With the emerging technologies and all associated devices, it is predicted that massive amount of data will be created in the next few years, in fact, as much as 90% of current data were created in the last couple of years,a trend that will continue for the foreseeable future. Sustainable computing studies the process by which computer engineer/scientist designs computers and associated subsystems efficiently and effectively with minimal impact on the environment. However, current intelligent machine-learning systems are performance driven, the focus is on the predictive/classification accuracy, based on known properties learned from the training samples. For instance, most machine-learning-based nonparametric models are known to require high computational cost in order to find the global optima. With the learning task in a large dataset, the number of hidden nodes within the network will therefore increase significantly, which eventually leads to an exponential rise in computational complexity. This paper thus reviews the theoretical and experimental data-modeling literature, in large-scale data-intensive fields, relating to: (1) model efficiency, including computational requirements in learning, and data-intensive areas structure and design, and introduces (2) new algorithmic approaches with the least memory requirements and processing to minimize computational cost, while maintaining/improving its predictive/classification accuracy and stability.