MAML2: meta reinforcement learning via meta-learning for task categories

Meta-learning has been widely applied to solving few-shot reinforcement learning problems, where we hope to obtain an agent that can learn quickly in a new task. However, these algorithms often ignore some isolated tasks in pursuit of the average performance, which may result in negative adaptation in these isolated tasks, and they usually need sufficient learning in a stationary task distribution. In this paper, our algorithm presents a hierarchical framework of double meta-learning, and the whole framework includes classification, meta-learning, and re-adaptation. Firstly, in the classification process, we classify tasks into several task subsets, considered as some categories of tasks, by learned parameters of each task, which can separate out some isolated tasks thereafter. Secondly, in the meta-learning process, we learn category parameters in all subsets via meta-learning. Simultaneously, based on the gradient of each category parameter in each subset, we use meta-learning again to learn a new meta-parameter related to the whole task set, which can be used as an initial parameter for the new task. Finally, in the re-adaption process, we adapt the parameter of the new task with two steps, by the meta-parameter and the appropriate category parameter successively. Experimentally, we demonstrate our algorithm prevents the agent from negative adaptation without losing the average performance for the whole task set. Additionally, our algorithm presents a more rapid adaptation process within re-adaptation. Moreover, we show the good performance of our algorithm with fewer samples as the agent is exposed to an online meta-learning setting.     

Sliding mode learning control for T-S fuzzy system and an application to hypersonic flight vehicle

Sliding mode-based learning control is presented for T-S fuzzy system. A T-S fuzzy model with both uncertainties and unmodeled dynamics is proposed firstly, in which the information of uncertainties and unmodeled dynamics are assumed to be unknown. Then, according to a given reference model, state-tracking error system is built. Respecting facts, the input matrices of the built T-S fuzzy model are different from each other. An extended state observer is built for estimating the unknown uncertainties and unmodeled dynamics, and a corresponding sliding surface is proposed. A learning controller is then presented for the closed loop system. Moreover, a numerical simulation result on hypersonic flight vehicles is considered to testify the controller's availability.     

An MRAS method for sensorless control of induction motor over a wide speed range

This paper addresses the problem of wide speed range sensorless control of induction motor.The proposed method is based on model reference adaptive system (MRAS),in which the current model serves as the adjustable model,and a novel hybrid model integrating the modified voltage model (MVM) and high-frequency signal injection method (HFSIM) are established to serve as the reference model.The HFSIM works together with MVM to improve the performance of the rotor speed and rotor flux position estimation at low speed,whereas at high speed,the MVM acts alone.In addition,a rotor resistance online estimation scheme is proposed to update the rotor resistance contained in the adjustable model and to ensure the estimation accuracy further.Experimental results show that the proposed MRAS method is very effective from low to high speed range,including zero speed.     

Investigating paper vs. screen in real-life hospital workflows: Performance contradicts perceived superiority of paper in the user experience

IntroductionAll hospitals in the province of Styria (Austria) are well equipped with sophisticated Information Technology, which provides all-encompassing on-screen patient information. Previous research made on the theoretical properties, advantages and disadvantages, of reading from paper vs. reading from a screen has resulted in the assumption that reading from a screen is slower, less accurate and more tiring. However, recent flat screen technology, especially on the basis of LCD, is of such high quality that obviously this assumption should now be challenged. As the electronic storage and presentation of information has many advantages in addition to a faster transfer and processing of the information, the usage of electronic screens in clinics should outperform the traditional hardcopy in both execution and preference ratings.This study took part in a County hospital Styria, Austria, with 111 medical professionals, working in a real-life setting. They were each asked to read original and authentic diagnosis reports, a gynecological report and an internal medical document, on both screen and paper in a randomly assigned order. Reading comprehension was measured by the Chunked Reading Test, and speed and accuracy of reading performance was quantified. In order to get a full understanding of the clinicians' preferences, subjective ratings were also collected.ResultsWilcoxon Signed Rank Tests showed no significant differences on reading performance between paper vs. screen. However, medical professionals showed a significant (90%) preference for reading from paper. Despite the high quality and the benefits of electronic media, paper still has some qualities which cannot provided electronically do date.     

High-performance cone beam reconstruction using CUDA compatible GPUs

Compute unified device architecture (CUDA) is a software development platform that allows us to run C-like programs on the nVIDIA graphics processing unit (GPU). This paper presents an acceleration method for cone beam reconstruction using CUDA compatible GPUs. The proposed method accelerates the Feldkamp, Davis, and Kress (FDK) algorithm using three techniques: (1) off-chip memory access reduction for saving the memory bandwidth; (2) loop unrolling for hiding the memory latency; and (3) multithreading for exploiting multiple GPUs. We describe how these techniques can be incorporated into the reconstruction code. We also show an analytical model to understand the reconstruction performance on multi-GPU environments. Experimental results show that the proposed method runs at 83% of the theoretical memory bandwidth, achieving a throughput of 64.3 projections per second (pps) for reconstruction of 512³-voxel volume from 360 512²-pixel projections. This performance is 41% higher than the previous CUDA-based method and is 24 times faster than a CPU-based method optimized by vector intrinsics. Some detailed analyses are also presented to understand how effectively the acceleration techniques increase the reconstruction performance of a naive method. We also demonstrate out-of-core reconstruction for large-scale datasets, up to 1024³-voxel volume.     

A blog emotion corpus for emotional expression analysis in Chinese

Weblogs are increasingly popular modes of communication and they are frequently used as mediums for emotional expression in the ever changing online world. This work uses blogs as object and data source for Chinese emotional expression analysis. First, a textual emotional expression space model is described, and based on this model, a relatively fine-grained annotation scheme is proposed for manual annotation of an emotion corpus. In document and paragraph levels, emotion category, emotion intensity, topic word and topic sentence are annotated. In sentence level, emotion category, emotion intensity, emotional keyword and phrase, degree word, negative word, conjunction, rhetoric, punctuation, objective or subjective, and emotion polarity are annotated. Then, using this corpus, we explore these linguistic expressions that indicate emotion in Chinese, and present a detailed data analysis on them, involving mixed emotions, independent emotion, emotion transfer, and analysis on words and rhetorics for emotional expression.     

Predication based immune network for multimodal function optimization

For the problem of indeterminate direction of local search, lacking of efficient regulation mechanism between local search and global search and regenerating new antibodies randomly in the original optimization version of artificial immune network (opt-aiNet), this paper puts forward a novel predication based immune network (PiNet) to solve multimodal function optimization more efficiently, accurately and reliably. The algorithm mimics natural phenomenon in immune system such as clonal selection, affinity maturation, immune network, immune memory and immune predication. The proposed algorithm includes two main features with opt-aiNet. The information of antibodies in continuous generations is utilized to point out the direction of local search and to adjust the balance between local and global search. PiNet also employs memory cells to generate new antibodies with high affinities. Theory analysis and experiments on 10 widely used benchmark problems show that when compared with opt-aiNet method, PiNet algorithm is capable of improving search performance significantly in successful rate, convergence speed, search ability, solution quality and algorithm stability.     

基于网格的数据挖掘算法

为了克服传统数据挖掘算法与分布式数据挖掘算法的不足．提出了一种基于网格平台的数据挖掘算法,并改进了原有的Apriori算法,使其应用于网格平台。基于网格的数据挖掘算法具有合并计算力,安全,高效,节约硬件成本等优势已越来越受到学术界的重视。     

An improved residual frequency offset estimation scheme for OFDM based WLAN systems

Coarse frequency offset estimate and tracking of residual frequency offset are two crucial stages for frequency synchronization in OFDM based WLAN systems. An improved frequency offset estimation scheme is proposed for tracking residual offset. The estimation scheme is dependent on the position of an OFDM symbol in a frame.     

Learning automatic concept detectors from online video

Concept detection is targeted at automatically labeling video content with semantic concepts appearing in it, like objects, locations, or activities. While concept detectors have become key components in many research prototypes for content-based video retrieval, their practical use is limited by the need for large-scale annotated training sets. To overcome this problem, we propose to train concept detectors on material downloaded from web-based video sharing portals like YouTube, such that training is based on tags given by users during upload, no manual annotation is required, and concept detection can scale up to thousands of concepts. On the downside, web video as training material is a complex domain, and the tags associated with it are weak and unreliable. Consequently, performance loss is to be expected when replacing high-quality state-of-the-art training sets with web video content.This paper presents a concept detection prototype named TubeTagger that utilizes YouTube content for an autonomous training. In quantitative experiments, we compare the performance when training on web video and on standard datasets from the literature. It is demonstrated that concept detection in web video is feasible, and that – when testing on YouTube videos – the YouTube-based detector outperforms the ones trained on standard training sets. By applying the YouTube-based prototype to datasets from the literature, we further demonstrate that: (1) If training annotations on the target domain are available, the resulting detectors significantly outperform the YouTube-based tagger. (2) If no annotations are available, the YouTube-based detector achieves comparable performance to the ones trained on standard datasets (moderate relative performance losses of 11.4% is measured) while offering the advantage of a fully automatic, scalable learning. (3) By enriching conventional training sets with online video material, performance improvements of 11.7% can be achieved when generalizing to domains unseen in training.