·844· 智能系统学报 第15卷 与记忆神经网络深度融合将是导航领域最有前景 [11]ZHANG Lei,WANG Shuai,LIU Bing.Deep learning for 的研究方向之一，最有希望实现空间地图的建 sentiment analysis:A survey[J].Wiley interdisciplinary 模，实现基于模型的强化学习。 reviews:data mining and knowledge discovery,2018, 8(4):e1253. 参考文献： [12]YOUNG T.HAZARIKA D.PORIA S.et al.Recent [1]刘强，段富海，桑勇.复杂环境下视觉SLAM闭环检测方 trends in deep learning based natural language 法综述[J.机器人，2019,41(1少112-123,136 processing[J].IEEE computational intelligence magazine, 2018.13(3):55-75. LIU Qiang,DUAN Fuhai,SANG Yong.A survey of loop- [13]OH J.CHOCKALINGAM V.SINGH S.et al.Control of closure detection method of visual SLAM in complex en- vironments[J].Robot,2019,41(1):112-123,136. memory,active perception,and action in minecraft[C]// Proceedings of the 33nd International Conference on Ma- [2]KULKARNI T D,SAEEDI A,GAUTAM S,et al.Deep chine Learning.New York,USA,2016:2790-2799 successor reinforcement learning[J].arXiv preprint arXiv: [14]BOTHE C,MAGG S,WEBER C,et al.Conversational 1606.02396v1,2016. analysis using utterance-level attention-based bidirection- [3]MNIH V.BADIA A P,MIRZA M,et al.Asynchronous al recurrent neural networks[C]//Proceedings of the 19th methods for deep reinforcement learning[C]//Proceedings Annual Conference of the International Speech Commu- of the 33rd International Conference on International Con- nication Association.Hyderabad,India,2018. ference on Machine Learning.New York,USA,2016: [15]张新生，高腾.多头注意力记忆网络的对象级情感分 1928-1937 类).模式识别与人工智能，2019,32(11)：997-1005. [4]ZHU Yuke,MOTTAGHI R,KOLVE E,et al.Target-driv- ZHANG Xinsheng,GAO Teng.Aspect level sentiment en visual navigation in indoor scenes using deep reinforce- classification with multiple-head attention memory net- ment learning[Cl//Proceedings of 2017 IEEE International work[J].Pattern recognition and artificial intelligence, Conference on Robotics and Automation (ICRA).Singa- 2019,32(11):997-1005 pore,2016. [16]BAHDANAU D,CHOROWSKI J,SERDYUK D,et al. [5]MIROWSKI P,PASCANU R,VIOLA F,et al.Learning to End-to-end attention-based large vocabulary speech re- navigate in complex environments[C]//Proceedings of the cognition[C]//Proceedings of 2016 IEEE International 5th International Conference on Learning Representations. Conference on Acoustics,Speech and Signal Processing. Toulon,France,2017. Shanghai,China,2016:4945-4949. [6]JADERBERG M,MNIH V,CZARNECKI W M,et al.Re- [17]JETLEY S,LORD N A,LEE N,et al.Learn to pay atten- inforcement learning with unsupervised auxiliary tasks[Cl// tion[C]//Proceedings of the 6th International Conference Proceedings of the 5th International Conference on Learn- on Learning Representations.Vancouver,Canada,2018. ing Representations.Toulon,France,2016 [18]梁天新，杨小平，王良，等.记忆神经网络的研究与发 [7]HEESS N,HUNT JJ,LILLICRAP T P,et al.Memory- 展).软件学报，2017,28(11)：2905-2924 based control with recurrent neural networks[C]//Proceed- LIANG Tianxin,YANG Xiaoping,WANG Liang,et al. ings of the Workshops of Advances in Neural Information Review on research and development of memory neural Processing Systems.Montreal,Canada,2015:301-312. networks[J].Journal of software,2017,28(11): [8]RAMANI D.A short survey on memory based reinforce- 2905-2924. ment learning[J].arXiv preprint arXiv:1904.06736v1, [19]TANG Duyu,QIN Bing,LIU Ting.Aspect level senti- 2019. ment classification with deep memory network[C]//Pro- [9]SAVINOV N,DOSOVITSKIY A,KOLTUN V.Semi- ceedings of the 2016 Conference on Empirical Methods in parametric topological memory for navigation[C]//Pro- Natural Language Processing.Austin,USA,2016. ceedings of the 6th International Conference on Learning [20]GRAVES A,WAYNE G,REYNOLDS M,et al.Hybrid Representations.Vancouver,Canada,2018. computing using a neural network with dynamic external [10]SUKHBAATAR A,WESTON J,FERGUS R,et al.End- memory[0.Nature,2016,538(7626):471-476. to-end memory networks[C]//Proceedings of the 28th In- [21]YANG Feng,ZHANG Shiyue,ZHANG Andi,et al. ternational Conference on Neural Information Processing Memory-augmented neural machine translation[C]//Pro- Systems.Montreal,Canada.2015:2440-2448 ceedings of the 2017 Conference on Empirical Methods in与记忆神经网络深度融合将是导航领域最有前景 的研究方向之一，最有希望实现空间地图的建 模，实现基于模型的强化学习。 参考文献： 刘强, 段富海, 桑勇. 复杂环境下视觉 SLAM 闭环检测方 法综述 [J]. 机器人, 2019, 41(1): 112–123, 136. LIU Qiang, DUAN Fuhai, SANG Yong. A survey of loop￾closure detection method of visual SLAM in complex en￾vironments[J]. Robot, 2019, 41(1): 112–123, 136. [1] KULKARNI T D, SAEEDI A, GAUTAM S, et al. Deep successor reinforcement learning[J]. arXiv preprint arXiv: 1606.02396v1, 2016. [2] MNIH V, BADIA A P, MIRZA M, et al. Asynchronous methods for deep reinforcement learning[C]//Proceedings of the 33rd International Conference on International Con￾ference on Machine Learning. New York, USA, 2016: 1928−1937. [3] ZHU Yuke, MOTTAGHI R, KOLVE E, et al. Target-driv￾en visual navigation in indoor scenes using deep reinforce￾ment learning[C]//Proceedings of 2017 IEEE International Conference on Robotics and Automation (ICRA). Singa￾pore, 2016. [4] MIROWSKI P, PASCANU R, VIOLA F, et al. Learning to navigate in complex environments[C]//Proceedings of the 5th International Conference on Learning Representations. Toulon, France, 2017. [5] JADERBERG M, MNIH V, CZARNECKI W M, et al. Re￾inforcement learning with unsupervised auxiliary tasks[C]// Proceedings of the 5th International Conference on Learn￾ing Representations. Toulon, France, 2016. [6] HEESS N, HUNT J J, LILLICRAP T P, et al. Memory￾based control with recurrent neural networks[C]//Proceed￾ings of the Workshops of Advances in Neural Information Processing Systems. Montreal, Canada, 2015: 301−312. [7] RAMANI D. A short survey on memory based reinforce￾ment learning[J]. arXiv preprint arXiv:1904.06736v1, 2019. [8] SAVINOV N, DOSOVITSKIY A, KOLTUN V. Semi￾parametric topological memory for navigation[C]//Pro￾ceedings of the 6th International Conference on Learning Representations. Vancouver, Canada, 2018. [9] SUKHBAATAR A, WESTON J, FERGUS R, et al. End￾to-end memory networks[C]//Proceedings of the 28th In￾ternational Conference on Neural Information Processing Systems. Montreal, Canada, 2015: 2440−2448. [10] ZHANG Lei, WANG Shuai, LIU Bing. Deep learning for sentiment analysis: A survey[J]. Wiley interdisciplinary reviews: data mining and knowledge discovery, 2018, 8(4): e1253. [11] YOUNG T, HAZARIKA D, PORIA S, et al. Recent trends in deep learning based natural language processing[J]. IEEE computational intelligence magazine, 2018, 13(3): 55–75. [12] OH J, CHOCKALINGAM V, SINGH S, et al. Control of memory, active perception, and action in minecraft[C]// Proceedings of the 33nd International Conference on Ma￾chine Learning. New York, USA, 2016: 2790−2799. [13] BOTHE C, MAGG S, WEBER C, et al. Conversational analysis using utterance-level attention-based bidirection￾al recurrent neural networks[C]//Proceedings of the 19th Annual Conference of the International Speech Commu￾nication Association. Hyderabad, India, 2018. [14] 张新生, 高腾. 多头注意力记忆网络的对象级情感分 类 [J]. 模式识别与人工智能, 2019, 32(11): 997–1005. ZHANG Xinsheng, GAO Teng. Aspect level sentiment classification with multiple-head attention memory net￾work[J]. Pattern recognition and artificial intelligence, 2019, 32(11): 997–1005. [15] BAHDANAU D, CHOROWSKI J, SERDYUK D, et al. End-to-end attention-based large vocabulary speech re￾cognition[C]//Proceedings of 2016 IEEE International Conference on Acoustics, Speech and Signal Processing. Shanghai, China, 2016: 4945−4949. [16] JETLEY S, LORD N A, LEE N, et al. Learn to pay atten￾tion[C]//Proceedings of the 6th International Conference on Learning Representations. Vancouver, Canada, 2018. [17] 梁天新, 杨小平, 王良, 等. 记忆神经网络的研究与发 展 [J]. 软件学报, 2017, 28(11): 2905–2924. LIANG Tianxin, YANG Xiaoping, WANG Liang, et al. Review on research and development of memory neural networks[J]. Journal of software, 2017, 28(11): 2905–2924. [18] TANG Duyu, QIN Bing, LIU Ting. Aspect level senti￾ment classification with deep memory network[C]//Pro￾ceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, USA, 2016. [19] GRAVES A, WAYNE G, REYNOLDS M, et al. Hybrid computing using a neural network with dynamic external memory[J]. Nature, 2016, 538(7626): 471–476. [20] YANG Feng, ZHANG Shiyue, ZHANG Andi, et al. Memory-augmented neural machine translation[C]//Pro￾ceedings of the 2017 Conference on Empirical Methods in [21] ·844· 智 能 系 统 学 报 第 15 卷