The Experts below are selected from a list of 135 Experts worldwide ranked by ideXlab platform
Sanja Fidler - One of the best experts on this subject based on the ideXlab platform.
-
Teaching Machines to describe images via natural language feedback
arXiv: Computation and Language, 2017Co-Authors: Huan Ling, Sanja FidlerAbstract:Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a learning agent in the form of natural language. We argue that a descriptive sentence can provide a much stronger learning signal than a numeric reward in that it can easily point to where the mistakes are and how to correct them. We focus on the problem of image captioning in which the quality of the output can easily be judged by non-experts. We propose a hierarchical phrase-based captioning model trained with policy gradients, and design a feedback network that provides reward to the learner by conditioning on the human-provided feedback. We show that by exploiting descriptive feedback our model learns to perform better than when given independently written human captions.
-
Teaching Machines to describe images with natural language feedback
Neural Information Processing Systems, 2017Co-Authors: Huan Ling, Sanja FidlerAbstract:Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a learning agent in the form of natural language. A descriptive sentence can provide a stronger learning signal than a numeric reward in that it can easily point to where the mistakes are and how to correct them. We focus on the problem of image captioning in which the quality of the output can easily be judged by non-experts. We propose a phrase-based captioning model trained with policy gradients, and design a critic that provides reward to the learner by conditioning on the human-provided feedback. We show that by exploiting descriptive feedback our model learns to perform better than when given independently written human captions.
Seon Joo Kim - One of the best experts on this subject based on the ideXlab platform.
-
Teaching Machines to understand baseball games large scale baseball video database for multiple video understanding tasks
European Conference on Computer Vision, 2018Co-Authors: Minho Shim, Young Hwi Kim, Kyung Min Kim, Seon Joo KimAbstract:A major obstacle in Teaching Machines to understand videos is the lack of training data, as creating temporal annotations for long videos requires a huge amount of human effort. To this end, we introduce a new large-scale baseball video dataset called the BBDB, which is produced semi-automatically by using play-by-play texts available online. The BBDB contains 4200\(+\)hr of baseball game videos with 400k\(+\) temporally annotated activity segments. The new dataset has several major challenging factors compared to other datasets: (1) the dataset contains a large number of visually similar segments with different labels. (2) It can be used for many video understanding tasks including video recognition, localization, text-video alignment, video highlight generation, and data imbalance problem. To observe the potential of the BBDB, we conducted extensive experiments by running many different types of video understanding algorithms on our new dataset. The database is available at https://sites.google.com/site/eccv2018bbdb/.
Huan Ling - One of the best experts on this subject based on the ideXlab platform.
-
Teaching Machines to describe images via natural language feedback
arXiv: Computation and Language, 2017Co-Authors: Huan Ling, Sanja FidlerAbstract:Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a learning agent in the form of natural language. We argue that a descriptive sentence can provide a much stronger learning signal than a numeric reward in that it can easily point to where the mistakes are and how to correct them. We focus on the problem of image captioning in which the quality of the output can easily be judged by non-experts. We propose a hierarchical phrase-based captioning model trained with policy gradients, and design a feedback network that provides reward to the learner by conditioning on the human-provided feedback. We show that by exploiting descriptive feedback our model learns to perform better than when given independently written human captions.
-
Teaching Machines to describe images with natural language feedback
Neural Information Processing Systems, 2017Co-Authors: Huan Ling, Sanja FidlerAbstract:Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a learning agent in the form of natural language. A descriptive sentence can provide a stronger learning signal than a numeric reward in that it can easily point to where the mistakes are and how to correct them. We focus on the problem of image captioning in which the quality of the output can easily be judged by non-experts. We propose a phrase-based captioning model trained with policy gradients, and design a critic that provides reward to the learner by conditioning on the human-provided feedback. We show that by exploiting descriptive feedback our model learns to perform better than when given independently written human captions.
Nese Sevim - One of the best experts on this subject based on the ideXlab platform.
-
adaptive learning systems beyond Teaching Machines
Contemporary Educational Technology, 2013Co-Authors: Nuri Kara, Nese SevimAbstract:Since 1950s, Teaching Machines have changed a lot. Today, we have different ideas about how people learn, what instructor should do to help students during their learning process. We have adaptive learning technologies that can create much more student oriented learning environments. The purpose of this article is to present these changes and its effects on learning environment. First, after explaining the concepts of Teaching Machines and adaptive learning systems including their main features as well as integral components, similarities and differences between these technologies are discussed briefly. Then, following the discussion on weaknesses and strengths of adaptive learning systems, what instructional designers should consider in developing and using them are mentioned.
Lili Tao - One of the best experts on this subject based on the ideXlab platform.
-
Teaching Machines to ask questions
International Joint Conference on Artificial Intelligence, 2018Co-Authors: Kaichun Yao, Libo Zhang, Tiejian Luo, Lili TaoAbstract:We propose a novel neural network model that aims to generate diverse and human-like natural language questions. Our model not only directly captures the variability in possible questions by using a latent variable, but also generates certain types of questions by introducing an additional observed variable. We deploy our model in the generative adversarial network (GAN) framework and modify the discriminator which not only allows evaluating the question authenticity, but predicts the question type. Our model is trained and evaluated on a question-answering dataset SQuAD, and the experimental results shown the proposed model is able to generate diverse and readable questions with the specific attribute.
