检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Iyer, Srinivasan Cheung, Alvin Zettlemoyer, Luke Paul G. Allen School of Computer Science and Engineering Univ. of Washington SeattleWA United States Department of Electrical Engineering and Computer Sciences UC Berkeley BerkeleyCA United States Facebook AI Research Seattle

Programmers typically organize executable source code using high-level coding patterns or idiomatic structures such as nested loops, exception handlers and recursive blocks, rather than as individual code tokens. In contrast, state of the art (SOTA) semantic parsers still map natural language instructions to source code by building the code syntax tree one node at a time. In this paper, we introduce an iterative method to extract code idioms from large source code corpora by repeatedly collapsing most-frequent depth-2 subtrees of their syntax trees, and train semantic parsers to apply these idioms during decoding. Applying idiom-based decoding on a recent contextdependent semantic parsing task improves the SOTA by 2.2% BLEU score while reducing training time by more than 50%. This improved speed enables us to scale up the model by training on an extended training set that is 5× larger, to further move up the SOTA by an additional 2.3% BLEU and 0.9% exact match. Finally, idioms also significantly improve accuracy of semantic parsing to SQL on the ATIS-SQL dataset, when training data is limited. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Optimization Landscapes for Overcomplete Representation Learning

arXiv

引用

arXiv 2019年

作者： Qu, Qing Zhai, Yuexiang Li, Xiao Zhang, Yuqian Zhu, Zhihui Center for Data Science New York University EECS Department UC Berkeley Silicon Valley Lab ByteDance Inc Department of Electronic Engineering Chinese University of Hong Kong Department of Electrical & Computer Engineering Rutgers University Mathematical Institute of Data Science Johns Hopkins University Department of Electrical & Computer Engineering University of Denver

We study nonconvex optimization landscapes for learning overcomplete representations, including learning (i) sparsely used overcomplete dictionaries and (ii) convolutional dictionaries, where these unsupervised learning problems find many applications in high-dimensional data analysis. Despite the empirical success of simple nonconvex algorithms, theoretical justifications of why these methods work so well are far from satisfactory. In this work, we show these problems can be formulated as `4-norm optimization problems with spherical constraint, and study the geometric properties of their nonconvex optimization landscapes. For both problems, we show the nonconvex objectives have benign geometric structures—every local minimizer is close to one of the target solutions and every saddle point exhibits negative curvature—either in the entire space or within a sufficiently large region. This discovery ensures local search algorithms (such as Riemannian gradient descent) with simple initializations approximately find the target solutions. Finally, numerical experiments justify our theoretical discoveries. Copyright © 2019, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

High-density memristor-CMOS ternary logic family

TechRxiv

引用

TechRxiv 2020年

作者： Wang, Xiaoyuan Zhou, Pengfei Eshraghian, Jason K. Lin, Chih-Yang Iu, Herbert Ho-Ching Chang, Ting-Chang Kang, Sung-Mo The School of Electronics and Information Hangzhou Dianzi University Hanzghou 310018 China The Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48105 United States The Department of Physics National Sun Yat-Sen University Kaohsiung80424 Taiwan The School of Electrical and Electronic Engineering The University of Western Australia Crawley WA6009 Australia The Jack Baskin School of Engineering UC Santa Cruz Santa CruzCA95064 United States

This paper presents the first experimental demonstration of a ternary memristor-CMOS logic family. We systematically design, simulate and experimentally verify the primitive logic functions: the ternary AND, OR and NOT gates. These are then used to build combinational ternary NAND, NOR, XOR and XNOR gates, as well as data handling ternary MAX and MIN gates. Our simulations are performed using a 50-nm process which are verified with in-house fabricated indium-tin-oxide memristors, optimized for fast switching, high transconductance, and low current leakage. We obtain close to an order of magnitude improvement in data density over conventional CMOS logic, and a reduction of switching speed by a factor of 13 over prior state-of-the-art ternary memristor results. We anticipate extensions of this work can realize practical implementation where high data density is of critical importance. © 2020, CC BY.

关键词： RRAM

来源：评论

学校读者我要写书评

暂无评论

PID2018 Benchmark Challenge: Multi-Objective Stochastic Optimization Algorithm

引用

IFAC-PapersOnLine 2018年第4期51卷 877-881页

作者： Ates, Abdullah Yuan, Jie Dehghan, Sina Zhao, Yang Yeroglu, Celaleddin Chen, YangQuan Inonu University Computer Engineering Department Malatya44280 Turkey School of Automation Southeast University Nanjing210096 China UC Merced Mechanical Engineering Departments MESA Lab MercedCA95301 United States School of Control Science and Engineering at Shandong University Jinan250061 China

This paper presents a multi-objective stochastic optimization method for tuning of the controller parameters of Refrigeration Systems based on Vapour Compression. Stochastic Multi Parameter Divergence Optimization (SMDO) algorithm is modified for minimization of the Multi Objective function for optimization process. System control performance is improved by tuning of the PI controller parameters according to discrete time model of the refrigeration system with multi objective function by adding conditional integral structure that is preferred to reduce the steady state error of the system. Simulations are compared with existing results via many graphical and numerical solutions. © 2018

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

Imitation from Observation: Learning to Imitate Behaviors fr...

引用

IEEE International Conference on Robotics and Automation

作者： YuXuan Liu Abhishek Gupta Pieter Abbeel Sergey Levine Department of Electrical Engineering and Computer Science UC Berkeley

Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator. However, standard imitation learning methods assume that the agent receives examples of observation-action tuples that could be provided, for instance, to a supervised learning algorithm. This stands in contrast to how humans and animals imitate: we observe another person performing some behavior and then figure out which actions will realize that behavior, compensating for changes in viewpoint, surroundings, object positions and types, and other factors. We term this kind of imitation learning "imitation-from-observation," and propose an imitation learning method based on video prediction with context translation and deep reinforcement learning. This lifts the assumption in imitation learning that the demonstration should consist of observations in the same environment configuration, and enables a variety of interesting applications, including learning robotic skills that involve tool use simply by observing videos of human tool use. Our experimental results show the effectiveness of our approach in learning a wide range of real-world robotic tasks modeled after common household chores from videos of a human demonstrator, including sweeping, ladling almonds, pushing objects as well as a number of tasks in simulation.

关键词： Task analysis Robots Context modeling Learning (artificial intelligence) Visualization Tools Cloning

来源：评论

学校读者我要写书评

暂无评论

Deep Object-Centric Representations for Generalizable Robot Learning

Deep Object-Centric Representations for Generalizable Robot ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Coline Devin Pieter Abbeel Trevor Darrell Sergey Levine UC Berkeley Department of Electrical Engineering and Computer Science

Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose using an object-centric prior and a semantic feature space for the perception system of a learned policy. We devise an object-level attentional mechanism that can be used to determine relevant objects from a few trajectories or demonstrations, and then immediately incorporate those objects into a learned policy. A task-independent attention locates possible objects in the scene, and a task-specific attention identifies which objects are predictive of the trajectories. The scope of the task-specific attention is easily adjusted by showing demonstrations with distractor objects or with diverse relevant objects. Our results indicate that this approach exhibits good generalization across object instances using very few samples, and can be used to learn a variety of manipulation tasks using reinforcement learning.

关键词： Task analysis Visualization Semantics Trajectory computer vision Standards

来源：评论

学校读者我要写书评

暂无评论

Meta learning shared hierarchies 6

Meta learning shared hierarchies

引用

6th International Conference on Learning Representations, ICLR 2018

作者： Frans, Kevin Ho, Jonathan Chen, Xi Abbeel, Pieter Schulman, John Henry M. Gunn High School United States UC Berkeley Department of Electrical Engineering and Computer Science United States OpenAI United States

We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives—policies that are executed for large numbers of timesteps. Specifically, a set of primitives are shared within a distribution of tasks, and are switched between by task-specific policies. We provide a concrete metric for measuring the strength of such hierarchies, leading to an optimization problem for quickly reaching high reward on unseen tasks. We then present an algorithm to solve this problem end-to-end through the use of any off-the-shelf reinforcement learning method, by repeatedly sampling new tasks and resetting task-specific policies. We successfully discover1 meaningful motor primitives for the directional movement of four-legged robots, solely by interacting with distributions of mazes. We also demonstrate the transferability of primitives to solve long-timescale sparse-reward obstacle courses, and we enable 3D humanoid robots to robustly walk and crawl with the same policy. © Learning Representations, ICLR 2018 - Conference Track *** right reserved.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Local binary pattern networks

arXiv

引用

arXiv 2018年

作者： Lin, Jeng-Hau Yang, Yunfan Gupta, Rajesh Tu, Zhuowen Department of Computer Science and Engineering UC San Diego Department of Cognitive Science UC San Diego

Memory and computation efficient deep learning architectures are crucial to continued proliferation of machine learning capabilities to new platforms and systems. Binarization of operations in convolutional neural networks has shown promising results in reducing model size and computing efficiency. In this paper, we tackle the problem using a strategy different from the existing literature by proposing local binary pattern networks or LBPNet, that is able to learn and perform binary operations in an end-to-end fashion. LBPNet1 uses local binary comparisons and random projection in place of conventional convolution (or approximation of convolution) operations. These operations can be implemented efficiently on different platforms including direct hardware implementation. We applied LBPNet and its variants on standard benchmarks. The results are promising across benchmarks while providing an important means to improve memory and speed efficiency that is particularly suited for small footprint devices and hardware accelerators. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?

arXiv

引用

arXiv 2025年

作者： Bucknall, Ben Siddiqui, Saad Thurnherr, Lara McGurk, Conor Harack, Ben Reuel, Anka Paskov, Patricia Mahoney, Casey Mindermann, Sören Singer, Scott Hiremath, Vinay Segerie, Charbel-Raphaël Delaney, Oscar Abate, Alessandro Barez, Fazl Cohen, Michael K. Torr, Philip Huszár, Ferenc Calinescu, Anisoara Jones, Gabriel Davis Bengio, Yoshua Trager, Robert Department of Engineering Science University of Oxford Oxford Martin AI Governance Initiative United Kingdom Safe AI Forum Oxford Martin AI Governance Initiative United Kingdom King’s College London United Kingdom Safe AI Forum United Kingdom Oxford Martin AI Governance Initiative United Kingdom Stanford University The Belfer Center for Science and International Affairs Harvard Kennedy School United States RAND Mila - Quebec AI Institute Canada Carnegie Endowment for International Peace Oxford Martin AI Governance Initiative United Kingdom Centre for the Governance of AI United Kingdom France Institute for AI Policy and Strategy Department of Computer Science University of Oxford United Kingdom Department of Engineering Science University of Oxford United Kingdom UC Berkeley Center for Human Compatible AI United States University of Cambridge United Kingdom Oxford Digital Health Labs University of Oxford United Kingdom Oxford Martin AI Governance Initiative Blavatnik School of Government University of Oxford United Kingdom

International cooperation is common in AI research, including between geopolitical rivals. While many experts advocate for greater international cooperation on AI safety to address shared global risks, some view cooperation on AI with suspicion, arguing that it can pose unacceptable risks to national security. However, the extent to which cooperation on AI safety poses such risks, as well as provides benefits, depends on the specific area of cooperation. In this paper, we consider technical factors that impact the risks of international cooperation on AI safety research, focusing on the degree to which such cooperation can advance dangerous capabilities, result in the sharing of sensitive information, or provide opportunities for harm. We begin by why nations historically cooperate on strategic technologies and analyse current US-China cooperation in AI as a case study. We further argue that existing frameworks for managing associated risks can be supplemented with consideration of key risks specific to cooperation on technical AI safety research. Through our analysis, we find that research into AI verification mechanisms and shared protocols may be suitable areas for such cooperation. Through this analysis we aim to help researchers and governments identify and mitigate the risks of international cooperation on AI safety research, so that the benefits of cooperation can be fully realised. © 2025, CC BY.

关键词： Safety engineering

来源：评论

学校读者我要写书评

暂无评论

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Sim-to-Real Transfer of Robotic Control with Dynamics Random...

引用

IEEE International Conference on Robotics and Automation

作者： Xue Bin Peng Marcin Andrychowicz Wojciech Zaremba Pieter Abbeel Department of Electrical Engineering and Computer Science UC Berkeley OpenAI

Simulations are attractive environments for training agents as they provide an abundant source of data and alleviate certain safety concerns during the training process. But the behaviours developed by agents in simulation are often specific to the characteristics of the simulator. Due to modeling error, strategies that are successful in simulation may not transfer to their real world counterparts. In this paper, we demonstrate a simple method to bridge this "reality gap". By randomizing the dynamics of the simulator during training, we are able to develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained. This adaptivity enables the policies to generalize to the dynamics of the real world without any training on the physical system. Our approach is demonstrated on an object pushing task using a robotic arm. Despite being trained exclusively in simulation, our policies are able to maintain a similar level of performance when deployed on a real robot, reliably moving an object to a desired location from random initial configurations. We explore the impact of various design decisions and show that the resulting policies are robust to significant calibration error.

关键词： Robots Training Adaptation models Task analysis Trajectory Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：