Search

A total of 320 1-day-old broilers were randomly divided into five groups. The control group (CON) received a basal diet, while the FAP4, FAP2, and FAP1 groups were provided with the basal diet supplemented with 4%, 2%, and 1% fermented Astragalus powder, respectively. The unfermented Astragalus powder (UAP2) group was fed the basal diet supplemented with 2% UAP. Each group contained eight replicates of eight chicks each. The results revealed that the final BW and ADG in the FAP 1 and FAP2 were higher than those in the UAP2 and CON groups, while reducing F/G from day 14 to day 42. On day 42, the thymus index in the UAP and FAP groups as well as the bursa index in the FAP4 group showed significant increases compared to those in the CON group. Supplementation with 2% FAP elevated serum IgA levels in broilers on day 28 and day 42, and it also increased serum IgG levels on day 42. Furthermore, supplementation with 2% FAP elevated serum albumin (ALB) levels in broilers, while supplementation with 4% FAP increased serum (glucose) GLU levels in broilers on day 28. The serum biochemical parameters and pathological observation of the liver and kidney in the groups did not show any adverse effects on broilers’ health. In addition, the serum total antioxidant capacity (T-AOC) level significantly increased in the FAP4 and FAP2 groups on day 28, and the malondialdehyde (MDA) level in both serum and liver tissue decreased in the FAP2 group on day 28 and day 42. Compared to the CON group, 2% FAP and 2% UAP supplementation reduced the relative abundance of Bacteroides and supplementation with 2% FAP increased the relative abundance of Alistipes on day 42. In conclusion, the dietary supplementation of FAP can enhance the growth performance, immune function, and antioxidant capacity and regulate microflora in broilers, of which 2% FAP is more effective. It indicates FAP exhibits significant application potential as a promising feed additive for broilers.

The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rewards to evaluate the significance of various primitive behaviors during training. We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Furthermore, to prevent excessive focus on specific primitive behaviors, we analyze the gradient dormancy phenomenon and introduce a dormancy-guided reset mechanism to further enhance the efficacy of our method. Our proposed algorithm, ACE: Off-policy Actor-critic with Causality-aware Entropy regularization, demonstrates a substantial performance advantage across 29 diverse continuous control tasks spanning 7 domains compared to model-free RL baselines, which underscores the effectiveness, versatility, and efficient sample efficiency of our approach. Benchmark results and videos are available at https://ace-rl.github.io/., Comment: Accepted by ICML 2024

The recent GAN inversion methods have been able to successfully invert the real image input to the corresponding editable latent code in StyleGAN. By combining with the language-vision model (CLIP), some text-driven image manipulation methods are proposed. However, these methods require extra costs to perform optimization for a certain image or a new attribute editing mode. To achieve a more efficient editing method, we propose a new Text-driven image Manipulation framework via Space Alignment (TMSA). The Space Alignment module aims to align the same semantic regions in CLIP and StyleGAN spaces. Then, the text input can be directly accessed into the StyleGAN space and be used to find the semantic shift according to the text description. The framework can support arbitrary image editing mode without additional cost. Our work provides the user with an interface to control the attributes of a given image according to text input and get the result in real time. Ex tensive experiments demonstrate our superior performance over prior works., Comment: 8 pages, 12 figures

Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite its progress, current algorithms are still unsatisfactory in virtually every aspect of the performance such as sample efficiency, asymptotic performance, and their robustness to the choice of random seeds. In this paper, we identify a major shortcoming in existing visual RL methods that is the agents often exhibit sustained inactivity during early training, thereby limiting their ability to explore effectively. Expanding upon this crucial observation, we additionally unveil a significant correlation between the agents' inclination towards motorically inactive exploration and the absence of neuronal activity within their policy networks. To quantify this inactivity, we adopt dormant ratio as a metric to measure inactivity in the RL agent's network. Empirically, we also recognize that the dormant ratio can act as a standalone indicator of an agent's activity level, regardless of the received reward signals. Leveraging the aforementioned insights, we introduce DrM, a method that uses three core mechanisms to guide agents' exploration-exploitation trade-offs by actively minimizing the dormant ratio. Experiments demonstrate that DrM achieves significant improvements in sample efficiency and asymptotic performance with no broken seeds (76 seeds in total) across three continuous control benchmark environments, including DeepMind Control Suite, MetaWorld, and Adroit. Most importantly, DrM is the first model-free algorithm that consistently solves tasks in both the Dog and Manipulator domains from the DeepMind Control Suite as well as three dexterous hand manipulation tasks without demonstrations in Adroit, all based on pixel observations., Comment: Accepted at The Twelfth International Conference on Learning Representations (ICLR 2024)

Pre-trained text-to-image generative models can produce diverse, semantically rich, and realistic images from natural language descriptions. Compared with language, images usually convey information with more details and less ambiguity. In this study, we propose Learning from the Void (LfVoid), a method that leverages the power of pre-trained text-to-image models and advanced image editing techniques to guide robot learning. Given natural language instructions, LfVoid can edit the original observations to obtain goal images, such as "wiping" a stain off a table. Subsequently, LfVoid trains an ensembled goal discriminator on the generated image to provide reward signals for a reinforcement learning agent, guiding it to achieve the goal. The ability of LfVoid to learn with zero in-domain training on expert demonstrations or true goal observations (the void) is attributed to the utilization of knowledge from web-scale generative models. We evaluate LfVoid across three simulated tasks and validate its feasibility in the corresponding real-world scenarios. In addition, we offer insights into the key considerations for the effective integration of visual generative models into robot learning workflows. We posit that our work represents an initial step towards the broader application of pre-trained visual generative models in the robotics field. Our project page: https://lfvoid-rl.github.io/.

Task requirements (TRs) writing is an important question type in Key English Test and Preliminary English Test. A TR writing question may include multiple requirements and a high-quality essay must respond to each requirement thoroughly and accurately. However, the limited teacher resources prevent students from getting detailed grading instantly. The majority of existing automatic essay scoring systems focus on giving a holistic score but rarely provide reasons to support it. In this paper, we proposed an end-to-end framework based on machine reading comprehension (MRC) to address this problem to some extent. The framework not only detects whether an essay responds to a requirement question, but clearly marks where the essay answers the question. Our framework consists of three modules: question normalization module, ELECTRA based MRC module and response locating module. We extensively explore state-of-the-art MRC methods. Our approach achieves 0.93 accuracy score and 0.85 F1 score on a real-world educational dataset. To encourage reproducible results, we make our code publicly available at \url{https://github.com/aied2021TRMRC/AIED_2021_TRMRC_code}., Comment: AIED'21: The 22nd International Conference on Artificial Intelligence in Education, 2021

Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR engines may introduce errors and inputs to downstream NLP models become noisy. Despite that pre-trained models achieve state-of-the-art performance in many NLP benchmarks, we prove that they are not robust to noisy texts generated by real OCR engines. This greatly limits the application of NLP models in real-world scenarios. In order to improve model performance on noisy OCR transcripts, it is natural to train the NLP model on labelled noisy texts. However, in most cases there are only labelled clean texts. Since there is no handwritten pictures corresponding to the text, it is impossible to directly use the recognition model to obtain noisy labelled data. Human resources can be employed to copy texts and take pictures, but it is extremely expensive considering the size of data for model training. Consequently, we are interested in making NLP models intrinsically robust to OCR errors in a low resource manner. We propose a novel robust training framework which 1) employs simple but effective methods to directly simulate natural OCR noises from clean texts and 2) iteratively mines the hard examples from a large number of simulated samples for optimal performance. 3) To make our model learn noise-invariant representations, a stability loss is employed. Experiments on three real-world datasets show that the proposed framework boosts the robustness of pre-trained models by a large margin. We believe that this work can greatly promote the application of NLP models in actual scenarios, although the algorithm we use is simple and straightforward. We make our codes and three datasets publicly available\footnote{https://github.com/tal-ai/Robust-learning-MSSHEM}., Comment: ECML-PKDD'21: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021

Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing representation learning approaches often require a large number of consistent and noise-free labels. However, due to various reasons such as budget constraints and privacy concerns, labels are very limited in many real-world scenarios. Directly applying standard representation learning approaches on small labeled data sets will easily run into over-fitting problems and lead to sub-optimal solutions. Even worse, in some domains such as education, the limited labels are usually annotated by multiple workers with diverse expertise, which yields noises and inconsistency in such crowdsourcing settings. In this paper, we propose a novel framework which aims to learn effective representations from limited data with crowdsourced labels. Specifically, we design a grouping based deep neural network to learn embeddings from a limited number of training samples and present a Bayesian confidence estimator to capture the inconsistency among crowdsourced labels. Furthermore, to expedite the training process, we develop a hard example selection procedure to adaptively pick up training examples that are misclassified by the model. Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines. In addition, we provide a comprehensive analysis on each of the main components of our proposed framework and also introduce the promising results it achieved in our real production to fully understand the proposed framework., Comment: IEEE Transactions on Knowledge and Data Engineering (Accepted)

Learning representation has been proven to be helpful in numerous machine learning tasks. The success of the majority of existing representation learning approaches often requires a large amount of consistent and noise-free labels. However, labels are not accessible in many real-world scenarios and they are usually annotated by the crowds. In practice, the crowdsourced labels are usually inconsistent among crowd workers given their diverse expertise and the number of crowdsourced labels is very limited. Thus, directly adopting crowdsourced labels for existing representation learning algorithms is inappropriate and suboptimal. In this paper, we investigate the above problem and propose a novel framework of \textbf{R}epresentation \textbf{L}earning with crowdsourced \textbf{L}abels, i.e., "RLL", which learns representation of data with crowdsourced labels by jointly and coherently solving the challenges introduced by limited and inconsistent labels. The proposed representation learning framework is evaluated in two real-world education applications. The experimental results demonstrate the benefits of our approach on learning representation from limited labeled data from the crowds, and show RLL is able to outperform state-of-the-art baselines. Moreover, detailed experiments are conducted on RLL to fully understand its key components and the corresponding performance.

Spoken language proficiency is critically important for children's growth and personal development. Due to the limited and imbalanced educational resources in China, elementary students barely have chances to improve their oral language skills in classes. Verbal fluency tasks (VFTs) were invented to let the students practice their spoken language proficiency after school. VFTs are simple but concrete math related questions that ask students to not only report answers but speak out the entire thinking process. In spite of the great success of VFTs, they bring a heavy grading burden to elementary teachers. To alleviate this problem, we develop Dolphin, a spoken language proficiency assessment system for Chinese elementary education. Dolphin is able to automatically evaluate both phonological fluency and semantic relevance of students' VFT answers. We conduct a wide range of offline and online experiments to demonstrate the effectiveness of Dolphin. In our offline experiments, we show that Dolphin improves both phonological fluency and semantic relevance evaluation performance when compared to state-of-the-art baselines on real-world educational data sets. In our online A/B experiments, we test Dolphin with 183 teachers from 2 major cities (Hangzhou and Xi'an) in China for 10 weeks and the results show that VFT assignments grading coverage is improved by 22\%., Comment: Proceedings of The Web Conference 2020 (WWW '20)

Polyvinylpyrrolidone–iodine (Povidone-iodine, PVP-I) is widely used as an antiseptic agent for lavation during joint surgery; however, the biological effects of PVP–I on cells from joint tissue are unknown. This study examined the biocompatibility and biological effects of PVP–I on cells from joint tissue, with the aim of optimizing cell-scaffold based joint repair. Cells from joint tissue, including cartilage derived progenitor cells (CPC), subchondral bone derived osteoblast and bone marrow derived mesenchymal stem cells (BM-MSC) were isolated. The concentration-dependent effects of PVP–I on cell proliferation, migration and differentiation were evaluated. Additionally, the efficacy and mechanism of a PVP–I loaded bilayer collagen scaffold for osteochondral defect repair was investigated in a rabbit model. A micromolar concentration of PVP–I was found not to affect cell proliferation, CPC migration or extracellular matrix production. Interestingly, micromolar concentrations of PVP–I promote osteogenic differentiation of BM-MSC, as evidenced by up-regulation of RUNX2 and Osteocalcin gene expression, as well as increased mineralization on the three-dimensional scaffold. PVP–I treatment of collagen scaffolds significantly increased fibronectin binding onto the scaffold surface and collagen type I protein synthesis of cultured BM-MSC. Implantation of PVP–I treated collagen scaffolds into rabbit osteochondral defect significantly enhanced subchondral bone regeneration at 6 weeks post-surgery compared with the scaffold alone (subchondral bone histological score of 8.80 ± 1.64 vs. 3.8 ± 2.19, p < 0.05). The biocompatibility and pro-osteogenic activity of PVP–I on the cells from joint tissue and the enhanced subchondral bone formation in PVP–I treated scaffolds would thus indicate the potential of PVP–I for osteochondral defect repair.

Plasmonic graphene is fabricated using thermally assisted self-assembly of silver nanoparticles on graphene. The localized surface-plasmonic effect is demonstrated with the resonance frequency shifting from 446 to 495 nm when the lateral dimension of the Ag nanoparticles increases from about 50 to 150 nm. Finite-difference time-domain simulations are employed to confirm the experimentally observed light-scattering enhancement in the solar spectrum in plasmonic graphene and the decrease of both the plasmonic resonance frequency and amplitude with increasing graphene thickness. In addition, plasmonic graphene shows much-improved electrical conductance by a factor of 2-4 as compared to the original graphene, making the plasmonic graphene a promising advanced transparent conductor with enhanced light scattering for thin-film optoelectronic devices., The original document contains color images. Published in Advanced Materials, v24 pOP71-OP76, 2012. Prepared in collaboration with the Department of Physics & Astronomy and Department of Engineering & Computer Science, University of Kansas, Lawrence, and the Materials Science Division, Argonne National Laboratory, Argonne, IL.

The quartz veins are fault-related structures in low-grade regionally metamorphosed Cambrian turbidites interlayered with mafic volcanics. Their non-planar geometry can be explained by their location as en echelon dilations in a shear system and by refraction across rheological interfaces in the sediments. The Early Devonian Stawell granite has contact metamorphosed the schists and first stage of mineralisation. Both Eastern and Western shears are anastomosed high-strain zones up to 50 m wide, connected at a high angle by mineralised structures. The lodes in the shear zones are oblique shear veins but the link structures are large-scale tensile fractures intitiated in a NE-SW crustal shortening episode. Subsequent deformation was accommodated by sinistral slip. A second stage of fluids, introduced after intrusion of the Stawell granite, focused along reverse faults and caused local retrogressive alteration and further gold mineralisation., The quartz veins are fault-related structures in low-grade regionally metamorphosed Cambrian turbidites interlayered with mafic volcanics. Their non-planar geometry can be explained by their location as en echelon dilations in a shear system and by refraction across rheological interfaces in the sediments. The Early Devonian Stawell granite has contact metamorphosed the schists and first stage of mineralisation. Both Eastern and Western shears are anastomosed high-strain zones up to 50 m wide, connected at a high angle by mineralised structures. The lodes in the shear zones are oblique shear veins but the link structures are large-scale tensile fractures intitiated in a NE-SW crustal shortening episode. Subsequent deformation was accommodated by sinistral slip. A second stage of fluids, introduced after intrusion of the Stawell granite, focused along reverse faults and caused local retrogressive alteration and further gold mineralisation.