show episodes
 
David Edmonds (Uehiro Centre, Oxford University) and Nigel Warburton (freelance philosopher/writer) interview top philosophers on a wide range of topics. Two books based on the series have been published by Oxford University Press. We are currently self-funding - donations very welcome via our website http://www.philosophybites.com
 
---- Situational Animations updated weekly. Stay tuned with us !! ---- We are a leading e-learning company specializing in publishing and producing textbooks, animations, games, mobile apps and customized services for all the Chinese learners. Website http://www.huayuschool.com Facebook http://www.facebook.com/HuayuSchool Twitter https://twitter.com/#!/TKBHuayuSchool App Blog http://apps2learnchinese.wordpress.com/ Youtube http://www.youtube.com/user/TKBHuayuSchool
 
China's most popular internet show follows the adventures of Su Fei as she looks for love in Beijing and meets lots of interesting characters along the way. Also other cool content about China, Chinese youth culture and music and interviews with notables, both Chinese and Expat. Features audio and video content.
 
What does it actually mean to be a feminist nowadays? Two Chinese teenagers in an American school bring their unique take on feminism to the table. If you’re struggling to establish your own identity as a feminist and would like to explore gender discrimination in the 21st century, this is the podcast for you!
 
Most true crime covers the past hundred years of recorded history. We cover the rest of it. From murderous knights and pirate kings to ancient Chinese forensic investigators and the Renaissance's literal fashion police, our episodic podcast dives deep into the historical characters and events that make up some of the greatest crimes the world has ever seen — and certainly not found in your textbooks. For more information visit https://www.highcrimesandhistory.com/
 
Cosy up with Rox and Jules as they chat about a range of topics such as careers, relationships, mental health, and more! What started from a zoom call to chat about their careers, quickly turned into realising they had similar dreams of starting a podcast. Sharing and discovering real stories from their Korean and Chinese Australian experience, this podcast is about two new friends learning about each other as much as it's about learning about themselves. You can also find them on Insta & YT ...
 
"Fast paced and full of energy" --Adrian Tchaikovsky, author of the Shadows of the Apt "This manuscript is full of highly crafted detail that will make readers shiver at times with fear and delight ... a familiar yet highly original fantasy that is a worthwhile read." -- Publishers Weekly "The real-world cultures are incredibly well-researched and truthful, and yet well-balanced with the fantasy elements. An intriguing and impressive series." -- Ben Galley, author of the Emaneska Series It i ...
 
Tune in to the healing wisdom of Nature with Flower Essence Practitioners Kathleen Aspenns and Rochana Felde. We share insights from years of practice and study to empower you to bring the healing qualities of Nature into your self care. Learn how to cultivate your vitality, reconnect with Nature’s wisdom and healing gifts, and soothe the stresses of modern life.
 
Oriental medicine was not developed in a laboratory. It does not advance through double-blind controlled studies, nor does it respond well to petri dish experimentation. Our medicine did not come from the statistical regression of randomized cohorts, but from the observation and treatment of individuals in their particular environment. It grows out of an embodied sense of understanding how life moves, unfolds, develops and declines. Medicine comes from continuous, thoughtful practice of what ...
 
The Suuuper Anime Podcast is a show that looks to entertain, inspire and inform you about anime. We provide our opinion and thoughts on various anime topics, as well examine these topics from a real-world perspective on what we can learn from anime. Whether you’re new to anime or a seasoned veteran, every week, we invite you to come listen, share and laugh with us :-). We hope every episode ignites your otaku spirit and leaves YOU feeling SUUUPER!
 
This little gem of a book was probably the first introduction to Shakespeare that most readers have had as children. Tales from Shakespeare was written in 1807 by a young clerk called Charles Lamb in the offices of the East India Company. Lamb co-authored them with his beloved sister Mary. The pair lived together for life, having gone through immense trauma caused by mental illness and tragedy. However, far from being a melancholy duo, they led an active and ample social life in the company ...
 
Set in England at the turn of the 20th century, Wallace’s crime novel The Daffodil Mystery follows the mysterious circumstances under which shop owner Lyne has been murdered. Accordingly, it is up to detective Jack Tarling and his trusted Chinese assistant to solve the case and reach an appropriate and just resolution. Moreover, the happenings within the novel are intensified by the colorful set of characters, which are marked by their plausible façade and contribute to the novel’s appeal. T ...
 
The Wine Australia podcast is all about sharing our passion for Australian wine. For those who love Australian wine we will share the stories of the people, the places and the communities that make our bold, authentic wines. For those sharing our Australian wines with the world we will share advice, insights and key learnings from thought leaders in the Australian wine community.
 
Loading …
show series
 
It has been just over two months since Nazanin Zaghari-Ratcliffe and Anoosheh Ashoori returned to the UK from detention in Iran, and were reunited with their families. But for the family of London born businessman and wildlife conservationist Morad Tahbaz it’s been a different story. The family said they expected their father to be part of the same…
 
Aaron Parisi, Yao Zhao, Noah FiedelAbstractTransformer based language models (LMs) demonstrate increasing performance with scale across a wide variety of tasks. Scale alone however cannot enable models to solve tasks that require access to ephemeral, changing, or private data that was unavailable at training time. Many useful tasks may also benefit…
 
Aitor Ormazabal, Mikel Artetxe, Manex Agirrezabal, Aitor Soroa and Eneko AgirreAbstractFormal verse poetry imposes strict constraints on the meter and rhyme scheme of poems. Most prior work on generating this type of poetry uses existing poems for supervision, which are difficult to obtain for most languages and poetic forms. In this work, we propo…
 
Aishwarya Agrawal, Ivana Kaji\'c, Emanuele Bugliarello, Elnaz Davoodi, Anita Gergely, Phil Blunsom, Aida NematzadehAbstractVision-and-language (V&L) models pretrained on large-scale multimodal data have demonstrated strong performance on various tasks such as image captioning and visual question answering (VQA). The quality of such models is common…
 
Xueying Bai, Jinghuan Shang, Yifan Sun, Niranjan BalasubramanianAbstractNLP models learn sentence representations for downstream tasks by tuning a model which is pre-trained by masked language modeling. However, after tuning, the learned sentence representations may be skewed heavily toward label space and thus are not expressive enough to represen…
 
Jiaqian Ren, Lei Jiang, Hao Peng, Zhiwei Liu, Jia Wu, Philip S. YuAbstractThe rising popularity of online social network services has attracted lots of research on mining social media data, especially on mining social events. Social event detection, due to its wide applications, has now become a trivial task. State-of-the-art approaches exploiting …
 
Glen Smith, Qiao Zhang, Christopher MacLellanAbstractComputer-aided diagnosis for medical imaging is a well-studied field that aims to provide real-time decision support systems for physicians. These systems attempt to detect and diagnose a plethora of medical conditions across a variety of image diagnostic technologies including ultrasound, x-ray,…
 
Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai ZhangAbstractThe increasingly stringent data privacy regulations limit the development of person re-identification (ReID) because person ReID training requires centralizing an enormous amount of data that contains sensitive personal information. To address this problem, we introduce federated person re-i…
 
Hanxu Zhou, Qixuan Zhou, Zhenyuan Jin, Tao Luo, Yaoyu Zhang, Zhi-Qin John XuAbstractSubstantial work indicates that the dynamics of neural networks (NNs) is closely related to their initialization of parameters. Inspired by the phase diagram for two-layer ReLU NNs with infinite width (Luo et al., 2021), we make a step towards drawing a phase diagra…
 
Pablo Mosteiro and Jesse Kuiper and Judith Masthoff and Floortje Scheepers and Marco SpruitAbstractFairness and bias are crucial concepts in artificial intelligence, yet they are relatively ignored in machine learning applications in clinical psychiatry. We computed fairness metrics and present bias mitigation strategies using a model trained on cl…
 
Georgios Tziafas, Hamidreza KasaeiAbstractService robots should be able to interact naturally with non-expert human users, not only to help them in various tasks but also to receive guidance in order to resolve ambiguities that might be present in the instruction. We consider the task of visual grounding, where the agent segments an object from a c…
 
Jenny Yang, Rasheed El-Bouri, Odhran O'Donoghue, Alexander S. Lachapelle, Andrew A. S. Soltan, David A. CliftonAbstractWith the rapid growth of memory and computing power, datasets are becoming increasingly complex and imbalanced. This is especially severe in the context of clinical data, where there may be one rare event for many cases in the majo…
 
Fan Wang, Weiming Liu, Chaochao Chen, Mengying Zhu, Xiaolin ZhengAbstractThe ever-increasing data scale of user-item interactions makes it challenging for an effective and efficient recommender system. Recently, hash-based collaborative filtering (Hash-CF) approaches employ efficient Hamming distance of learned binary representations of users and i…
 
Katharina Hoedt, Arthur Flexer, Gerhard WidmerAbstractAdversarial attacks can drastically degrade performance of recommenders and other machine learning systems, resulting in an increased demand for defence mechanisms. We present a new line of defence against attacks which exploit a vulnerability of recommenders that operate in high dimensional dat…
 
Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright, Michael Bowling, Amy R. GreenwaldAbstractHindsight rationality is an approach to playing general-sum games that prescribes no-regret learning dynamics for individual agents with respect to a set of deviations, and further describes jointly rational behavior among multiple agents with med…
 
Jianhan Wu, Shijing Si, Jianzong Wang, Jing XiaoAbstractWith the rapid development of the Metaverse, virtual humans have emerged, and human image synthesis and editing techniques, such as pose transfer, have recently become popular. Most of the existing techniques rely on GANs, which can generate good human images even with large variants and occlu…
 
Emmanuel Dauc\'eAbstractThe capability to widely sample the state and action spaces is a key ingredient toward building effective reinforcement learning algorithms. The variational optimization principles exposed in this paper emphasize the importance of an occupancy model to synthesizes the general distribution of the agent's environmental states …
 
Tomer Barak and Yonatan LoewensteinAbstractCognitive psychologists often use the term $\textit{fluid intelligence}$ to describe the ability of humans to solve novel tasks without any prior training. In contrast to humans, deep neural networks can perform cognitive tasks only after extensive (pre-)training with a large number of relevant examples. M…
 
Yuan Wang and Huiling Song and Peng Huo and Tao Xu and Jucheng Yang and Yarui Chen and Tingting ZhaoAbstractExtreme multi-label text classification (XMTC) refers to the problem of tagging a given text with the most relevant subset of labels from a large label set. A majority of labels only have a few training instances due to large label dimensiona…
 
Buda Baji\'c, Ozan \"Oktem, Jevgenija RudzusikaAbstractHelical acquisition geometry is the most common geometry used in computed tomography (CT) scanners for medical imaging. We adapt the invertible Learned Primal-Dual (iLPD) deep neural network architecture so that it can be applied to helical 3D CT reconstruction. We achieve this by splitting the…
 
Sometimes our curious venture into solving our problems lures us to overstep the boundaries we did not realize were important. A need to control pain may leave you chained to pain medication. An attempt to numb life stressors may plunge you into alcoholism. Solving a problem in the immediate moment, could lead us into habits that over time wear on …
 
Kawin Ethayarajh, Dan JurafskyAbstractHuman ratings are treated as the gold standard in NLG evaluation. The standard protocol is to collect ratings of generated text, average across annotators, and then rank NLG systems by their average scores. However, little consideration has been given as to whether this approach faithfully captures human prefer…
 
Amirhoshang Hoseinpour Dehkordi, Majid Alizadeh, Ali MovagharAbstractIn this note, a formal transition system model called LTPAL to extract knowledge in a classification process is suggested. The model combines the Public Announcement Logic (PAL) and the Linear Temporal Logic (LTL). In the model, first, we consider classifiers, which capture single…
 
Aldi Piroli, Vinzenz Dallabetta, Marc Walessa, Daniel Meissner, Johannes Kopp, Klaus DietmayerAbstractAdverse weather conditions can negatively affect LiDAR-based object detectors. In this work, we focus on the phenomenon of vehicle gas exhaust condensation in cold weather conditions. This everyday effect can influence the estimation of object size…
 
Yuhan Li, Wei Shen, Jianbo Gao, Yadong WangAbstractCommunity Question Answering (CQA) platforms contain plenty of CQA texts (i.e., questions and answers corresponding to the question) where named entities appear ubiquitously. In this paper, we define a new task of CQA entity linking (CQAEL) as linking the textual entity mentions detected from CQA t…
 
Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke IwasawaAbstractPretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (CoT) prompting, a recent technique for elicit…
 
Lang Qian, Shengjie Zheng, Chunshan Deng, Cheng Yang, Xiaojian LiAbstractBrain-computer interfaces (BCIs), is ways for electronic devices to communicate directly with the brain. For most medical-type brain-computer interface tasks, the activity of multiple units of neurons or local field potentials is sufficient for decoding. But for BCIs used in n…
 
Wei Gao, Qinghao Hu, Zhisheng Ye, Peng Sun, Xiaolin Wang, Yingwei Luo, Tianwei Zhang, Yonggang WenAbstractDeep learning (DL) shows its prosperity in a wide variety of fields. The development of a DL model is a time-consuming and resource-intensive procedure. Hence, dedicated GPU accelerators have been collectively constructed into a GPU datacenter.…
 
Zhenhe Cui, Weidu Kuang, Yongmei LiuAbstractGeneralized planning studies the computation of general solutions for a set of planning problems. Computing general solutions with correctness guarantee has long been a key issue in generalized planning. Abstractions are widely used to solve generalized planning problems. Solutions of sound abstractions a…
 
Jennifer D'SouzaAbstractWe are faced with an unprecedented production in scholarly publications worldwide. Stakeholders in the digital libraries posit that the document-based publishing paradigm has reached the limits of adequacy. Instead, structured, machine-interpretable, fine-grained scholarly knowledge publishing as Knowledge Graphs (KG) is str…
 
Zifan Wang, Yuhang Yao, Chaoran Zhang, Han Zhang, Youjie Kang, Carlee Joe-Wong, Matt Fredrikson, Anupam DattaAbstractThis paper studies faithful explanations for Graph Neural Networks (GNNs). First, we provide a new and general method for formally characterizing the faithfulness of explanations for GNNs. It applies to existing explanation methods, …
 
Junyong Wang, Yuan Zeng and Yi GongAbstractAccurate detection of objects in 3D point clouds is a key problem in autonomous driving systems. Collaborative perception can incorporate information from spatially diverse sensors and provide significant benefits for improving the perception accuracy of autonomous driving systems. In this work, we conside…
 
Yusuke Urakami, Alec Hodgkinson, Casey Carlin, Randall Leu, Luca Rigazio, Pieter AbbeelAbstractIn order to practically implement the door opening task, a policy ought to be robust to a wide distribution of door types and environment settings. Reinforcement Learning (RL) with Domain Randomization (DR) is a promising technique to enforce policy gener…
 
Zhiwei Hao, Yong Luo, Zhi Wang, Han Hu, Jianping AnAbstractRecently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for compression, its requirement on the original datase…
 
Linrui zhang, Li Shen, Long Yang, Shixiang Chen, Bo Yuan, Xueqian Wang, Dacheng TaoAbstractSafe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications. However, current algorithms still struggle for efficient policy updates with hard constraint satisfaction. In this…
 
George P. Harabin, Morad BehandishAbstractHybrid manufacturing (HM) technologies combine additive and subtractive manufacturing (AM/SM) capabilities in multi-modal process plans that leverage the strengths of each. Despite the growing interest in HM technologies, software tools for process planning have not caught up with advances in hardware and t…
 
Lesheng Jin, Zihan Wang, Jingbo ShangAbstractExisting backdoor defense methods are only effective for limited trigger types. To defend different trigger types at once, we start from the class-irrelevant nature of the poisoning process and propose a novel weakly supervised backdoor defense framework WeDef. Recent advances in weak supervision make it…
 
Keehang KwonAbstract{\em Computability logic} (CoL) is a powerful computational model which views computational problems as games played by a machine and its environment. It uses formulas to represent computational problems. In this paper, we show that CoL naturally supports multiagent programming models with distributed control. To be specific, we…
 
Zihan Wang, Kewen Zhao, Zilong Wang, Jingbo ShangAbstractFine-tuning pre-trained language models has recently become a common practice in building NLP models for various tasks, especially few-shot tasks. We argue that under the few-shot setting, formulating fine-tuning closer to the pre-training objectives shall be able to unleash more benefits fro…
 
Jiachen Li, Ye Yuan, Hong-Bin ShenAbstractSymbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data. Currently, SR still basically relies on various searching strategies so that a sample-specific model is required to be optimized for every expression, which significantly limi…
 
Liping Hou, Ke Lu, Xue Yang, Yuqiu Li, Jian XueAbstractArbitrary-oriented object representations contain the oriented bounding box (OBB), quadrilateral bounding box (QBB), and point set (PointSet). Each representation encounters problems that correspond to its characteristics, such as the boundary discontinuity, square-like problem, representation …
 
Zhendong Chu, Hongning Wang, Yun Xiao, Bo Long, Lingfei WuAbstractConversational recommender systems (CRS) explicitly solicit users' preferences for improved recommendations on the fly. Most existing CRS solutions employ reinforcement learning methods to train a single policy for a population of users. However, for users new to the system, such a g…
 
“I’m never doing content because I think it will bring in views. I’m doing content if it’s something I am actively interested in that I want to find out more about or that I enjoy.” – RogersBase WARNING! This episode might trigger you! For our 100th episode, we had the amazing and talented Anime YouTuber and content creator RogersBase! This episode…
 
Mingzhe Sui, Hanting Li, Zhaoqing Zhu, and Feng ZhaoAbstract2D+3D facial expression recognition (FER) can effectively cope with illumination changes and pose variations by simultaneously merging 2D texture and more robust 3D depth information. Most deep learning-based approaches employ the simple fusion strategy that concatenates the multimodal fea…
 
Hideya Ochiai, Yuwei Sun, Qingzhe Jin, Nattanon Wongwiwatchai, Hiroshi EsakiAbstractFederated learning has allowed training of a global model by aggregating local models trained on local nodes. However, it still takes client-server model, which can be further distributed, fully decentralized, or even partially connected, or totally opportunistic. I…
 
Davor Runje, Sharath M. ShankaranarayanaAbstractDeep neural networks are becoming increasingly popular in approximating arbitrary functions from noisy data. But wider adoption is being hindered by the need to explain such models and to impose additional constraints on them. Monotonicity constraint is one of the most requested properties in real-wor…
 
Banghua Zhu, Lun Wang, Qi Pang, Shuai Wang, Jiantao Jiao, Dawn Song, Michael I. JordanAbstractWe propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the parameters for stron…
 
Jialiang Wang, Haotian Wei, Yi Wang, Shu Yang, Chi LiAbstractHuman activity recognition (HAR) based on multimodal sensors has become a rapidly growing branch of biometric recognition and artificial intelligence. However, how to fully mine multimodal time series data and effectively learn accurate behavioral features has always been a hot topic in t…
 
Loading …

Quick Reference Guide

Copyright 2022 | Sitemap | Privacy Policy | Terms of Service
Google login Twitter login Classic login