Austenite isothermal transformation curve (IT) of steel, also known as time-temperature-transformation curve (TTT) is an very important basic data for the heat treatment process design of steel. Traditionally, obtaini...
详细信息
Learners' affective states play a crucial role in learning evaluation, and the external expressions that can directly reflect affect are facial expressions. However, the sample size of the database for the learnin...
详细信息
Prior work has shown the classification of voiding dysfunctions from uroflowmeter data using machinelearning. We present the use of smartwatch audio, collected through the UroSound platform, in order to automatically...
详细信息
ISBN:
(数字)9781728127828
ISBN:
(纸本)9781728127828
Prior work has shown the classification of voiding dysfunctions from uroflowmeter data using machinelearning. We present the use of smartwatch audio, collected through the UroSound platform, in order to automatically classify voiding signals as normal or abnormal, using classical machinelearning techniques. We train several classification models using classical machinelearning and report a maximal test accuracy of 86.16% using an ensemble method classifier.
A major progression in sensor-based technologies has resulted in a fast evolution of the Internet of Things (IoT) applications for developing any real-time monitoring systems. Nowadays, an increasing number of aged pe...
详细信息
With the development of social media, there are more and more platforms for people to express their opinions and ideas openly, so there are more and more comments on the same thing and event from different angles on t...
详细信息
In recent years, the issue of credit fraud risk has garnered increased attention from the banking and financial sectors. However, prevailing credit assessment models predominantly focus on predictive outcomes, often o...
详细信息
Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machinelearning models in real-world applications. Previous paradigms either explore better scoring functions or utilize the ...
详细信息
Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machinelearning models in real-world applications. Previous paradigms either explore better scoring functions or utilize the knowledge of outliers to equip the models with the ability of OOD detection. However, few of them pay attention to the intrinsic OOD detection capability of the given model. In this work, we generally discover the existence of an intermediate stage of a model trained on in-distribution (ID) data having higher OOD detection performance than that of its final stage across different settings, and further identify one critical data-level attribution to be learning with the atypical samples. Based on such insights, we propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data. Our method utilizes a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them. Extensive experiments and analysis demonstrate the effectiveness of our method. The code is available at: https://***/ tmlr- group/Unleashing- Mask.
In recent years, the field of computer networks and the internet has experienced exponential growth. At the same time, it also raises issues with respect to security. The standard responsive techniques, such as antivi...
详细信息
The world of Big data has been rapidly expanding into the domains of engineering and machinelearning. The biggest challenge in the Big data landscape is the incompetence of processing vast amounts of data in a time-e...
详细信息
Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. So learning robotic tasks from pre-collected d...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. So learning robotic tasks from pre-collected data is a promising direction. Agile and stable legged locomotion remains an open issue in its general form. Analogous to the rapid progress of supervised learning in recent years, the combination of offline reinforcement learning (ORL) and realistic datasets has the potential to make breakthroughs in this challenging field. To facilitate the ORL research for real-world applications, we benchmark ten ORL algorithms in the realistic quadrupedal locomotion dataset. The dataset is collected by the classical model predictive control (MPC) method, rather than the online RL method commonly utilized by previous ORL benchmarks. Extensive experimental results show that the best-performing ORL algorithms can achieve competitive performance compared with the online RL, and even surpass it in some tasks. However, there is still a gap between the learning-based methods and classical MPC, especially in terms of stability and task response accuracy. Our benchmark can provide a fertile ground for future application-oriented ORL research.
暂无评论