检索结果-内蒙古大学图书馆

Neural assistant: Joint action prediction, response generation, and latent knowledge reasoning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Neelakantan, Arvind Yavuz, Semih Narang, Sharan Prasad, Vishaal Goodrich, Ben Duckworth, Daniel Sankar, Chinnadhurai Yan, Xifeng Google Salesforce Montreal Institute for Learning Algorithms UC Santa Barbara

Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin by converting conversation history to a symbolic object referred to as belief state by using supervised learning. The belief state is then used to reason on an external knowledge source whose result along with the conversation history is used in action prediction and response generation tasks independently. Such a pipeline of individually optimized components not only makes the development process cumbersome but also makes it non-trivial to leverage session-level user reinforcement signals. In this paper, we develop Neural Assistant: a single neural network model that takes conversation history and an external knowledge source as input and jointly produces both text response and action to be taken by the system as output. The model learns to reason on the provided knowledge source with weak supervision signal coming from the text generation and the action prediction tasks, hence removing the need for belief state annotations. In the MultiWOZ dataset, we study the effect of distant supervision, and the size of knowledge base on model performance. We find that the Neural Assistant without belief states is able to incorporate external knowledge information achieving higher factual accuracy scores compared to Transformer. In settings comparable to reported baseline systems, Neural Assistant when provided with oracle belief state significantly improves language generation performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Knowledge based systems

Plug and play generative networks: Conditional iterative generation of images in latent space 30

学校读者我要写书评

暂无评论

Plug and play generative networks: Conditional iterative gen...

30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

作者： Nguyen, Anh Clune, Jeff Bengio, Yoshua Dosovitskiy, Alexey Yosinski, Jason University of Wyoming United States Uber AI Labs University of Wyoming United States Montreal Institute for Learning Algorithms Canada University of Freiburg Germany Uber AI Labs Canada

ISBN: (纸本)9781538604571

Generating high-resolution, photo-realistic images has been a long-standing goal in machine learning. Recently, Nguyen et al. [37] showed one interesting way to synthesize novel images by performing gradient ascent in the latent space of a generator network to maximize the activations of one or multiple neurons in a separate classifier network. In this paper we extend this method by introducing an additional prior on the latent code, improving both sample quality and sample diversity, leading to a state-of-the-art generative model that produces high quality images at higher resolutions (227 × 227) than previous generative models, and does so for all 1000 ImageNet categories. In addition, we provide a unified probabilistic interpretation of related activation maximization methods and call the general class of models "Plug and Play Generative Networks." PPGNs are composed of 1) a generator network G that is capable of drawing a wide range of image types and 2) a replaceable "condition" network C that tells the generator what to draw. We demonstrate the generation of images conditioned on a class (when C is an ImageNet or MIT Places classification network) and also conditioned on a caption (when C is an image captioning network). Our method also improves the state of the art of Multifaceted Feature Visualization [40], which generates the set of synthetic inputs that activate a neuron in order to better understand how deep neural networks operate. Finally, we show that our model performs reasonably well at the task of image inpainting. While image models are used in this paper, the approach is modality-agnostic and can be applied to many types of data. © 2017 IEEE.

关键词： Chemical activation

Understanding Plasticity in Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lyle, Clare Zheng, Zeyu Nikishin, Evgenii Pires, Bernardo Avila Pascanu, Razvan Dabney, Will Google DeepMind United Kingdom Montreal Institute for Learning Algorithms Canada

Plasticity, the ability of a neural network to quickly change its predictions in response to new information, is essential for the adaptability and robustness of deep reinforcement learning systems. Deep neural networks are known to lose plasticity over the course of training even in relatively simple learning problems, but the mechanisms driving this phenomenon are still poorly understood. This paper conducts a systematic empirical analysis into plasticity loss, with the goal of understanding the phenomenon mechanistically in order to guide the future development of targeted solutions. We find that loss of plasticity is deeply connected to changes in the curvature of the loss landscape, but that it often occurs in the absence of saturated units. Based on this insight, we identify a number of parameterization and optimization design choices which enable networks to better preserve plasticity over the course of training. We validate the utility of these findings on larger-scale RL benchmarks in the Arcade learning Environment. © 2023, CC BY.

关键词： Deep neural networks

Improved training of wasserstein GANs

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Gulrajani, Ishaan Ahmed, Faruk Arjovsky, Martin Dumoulin, Vincent Courville, Aaron Montreal Institute for Learning Algorithms Courant Institute of Mathematical Sciences CIFAR Google Brain

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only poor samples or fail to converge. We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior. We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input. Our proposed method performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning, including 101-layer ResNets and language models with continuous generators. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

Machine comprehension by text-to-text neural question generation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yuan, Xingdi Wang, Tong Gulcehre, Caglar Sordoni, Alessandro Bachman, Philip Subramanian, Sandeep Zhang, Saizheng Trischler, Adam Microsoft Maluuba Montreal Institute for Learning Algorithms Université de Montréal

We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. Our model is trained and evaluated on the recent question-answering dataset SQuAD. Copyright © 2017, The Authors. All rights reserved.

关键词： Maximum likelihood

A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Alami, Reda Mahfoud, Mohammed Achab, Mastane Technology Innovation Institute Masdar City United Arab Emirates Montreal Institute for Learning Algorithms Montreal Canada

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon T. While the choice of a strategy that accomplishes that is optimal with no additional information, it is no longer the case when provided additional environment-specific knowledge. In particular, in areas of high volatility like healthcare or finance, a naive reward maximization approach often does not accurately capture the complexity of the learning problem and results in unreliable solutions. To tackle problems of this nature, we propose a framework of adaptive risk-aware strategies that operate in non-stationary environments. Our framework incorporates various risk measures prevalent in the literature to map multiple families of multi-armed bandit algorithms into a risk-sensitive setting. In addition, we equip the resulting algorithms with the Restarted Bayesian Online Change-Point Detection (R-BOCPD) algorithm and impose a (tunable) forced exploration strategy to detect local (per-arm) switches. We provide finite-time theoretical guarantees and an asymptotic regret bound of Õ(√KTT) up to time horizon T with KT the total number of change-points. In practice, our framework compares favorably to the state-of-the-art in both synthetic and real-world environments and manages to perform efficiently with respect to both risk-sensitivity and non-stationarity. Copyright © 2023, The Authors. All rights reserved.

关键词： Risk assessment

A deep reinforcement learning chatbot (short version)

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Serban, Iulian V. Sankar, Chinnadhurai Germain, Mathieu Zhang, Saizheng Lin, Zhouhan Subramanian, Sandeep Kim, Taesup Pieper, Michael Chandar, Sarath Ke, Nan Rosemary Rajeswar, Sai de Brebisson, Alexandre Sotelo, Jose M.R. Suhubdy, Dendi Michalski, Vincent Nguyen, Alexandre Pineau, Joelle Bengio, Yoshua Montreal Institute for Learning Algorithms MontrealQC Canada School of Computer Science McGill University CIFAR

We present MILABOT: a deep reinforcement learning chatbot developed by the montreal institute for learning algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including neural network and template-based models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than other systems. The results highlight the potential of coupling ensemble systems with deep reinforcement learning as a fruitful path for developing real-world, open-domain conversational agents. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

learning the joint representation of heterogeneous temporal events for clinical endpoint prediction

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Luchen Shen, Jianhao Zhang, Ming Wang, Zichang Tang, Jian School of EECS Peking University Beijing China HEC Montreal Canada Montreal Institute for Learning Algorithms

The availability of a large amount of electronic health records (EHR) provides huge opportunities to improve health care service by mining these data. One important application is clinical endpoint prediction, which aims to predict whether a disease, a symptom or an abnormal lab test will happen in the future according to patients’ history records. This paper develops deep learning techniques for clinical endpoint prediction, which are effective in many practical applications. However, the problem is very challenging since patients’ history records contain multiple heterogeneous temporal events such as lab tests, diagnosis, and drug administrations. The visiting patterns of different types of events vary significantly, and there exist complex nonlinear relationships between different events. In this paper, we propose a novel model for learning the joint representation of heterogeneous temporal events. The model adds a new gate to control the visiting rates of different events which effectively models the irregular patterns of different events and their nonlinear correlations. Experiment results with real-world clinical data on the tasks of predicting death and abnormal lab tests prove the effectiveness of our proposed approach over competitive baselines. Copyright © 2018, The Authors. All rights reserved.

关键词： Diagnosis

*** - Reproducing intuition

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cohen, Joseph Paul Lo, Henry Z. Institute for Reproducible Research Montreal Institute for Learning Algorithms Université of Montréal Institute for Reproducible Research

We present ***, a platform for post-publication discussion of research papers. On ***, the research community can read and write summaries of papers in order to increase accessible and reproducibility. Summaries contain the perspective and insight of other readers, why they liked or disliked it, and their attempt to demystify complicated sections. *** has over 600 paper summaries, all of which are searchable and organized by paper, conference, and year. Many regular contributors are expert machine learning researchers. We present statistics from the last year of operation, user demographics, and responses from a usage survey. Results indicate that ShortScience benefits students most, by providing short, understandable summaries reflecting expert opinions. Copyright © 2017, The Authors. All rights reserved.

关键词： Paper