2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)最新文献_第2页

Bayesian Noisy Word Clustering through Sampling Prototypical Words 基于采样原型词的贝叶斯噪声词聚类

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8760503

T. Taniguchi, Yuta Fukusako, Toshiaki Takano

{"title":"Bayesian Noisy Word Clustering through Sampling Prototypical Words","authors":"T. Taniguchi, Yuta Fukusako, Toshiaki Takano","doi":"10.1109/DEVLRN.2018.8760503","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8760503","url":null,"abstract":"This paper describes a new algorithm for sampling prototypical words from a set of noisy words and proposes a noisy word clustering method. In a lexical acquisition task, phoneme sequences recognized by a developmental robot using a phoneme recognizer have many errors. A letter or phoneme sequence involving errors is called a noisy word. To develop a mixture model for noisy words and develop a clustering method, a procedure needs to be developed for the sampling of a prototypical word, i.e., “mean” string, in a cluster of noisy words. Despite a long history regarding methods for treating noisy words, e.g., a stochastic deformation model, the edit distance and their variants, and an efficient sampling procedure for prototypical words have not been developed. In this paper, the mixture of stochastic deformation models, namely a generative model for noisy words, is proposed, and efficient blocked Gibbs samplers for the model are proposed. To develop this procedure, a forward filtering backward sampling procedure is proposed for jointly decoding noisy words and sampling their “mean” string. We applied the proposed clustering method to a set of noisy synthetic words and obtained better results than a baseline method. In particular, a sampling procedure using tied backward sampling demonstrated the best performance in reconstructing original words from noisy words through a clustering process.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127609974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Solving Bidirectional Tasks using MTRNN 利用MTRNN解决双向任务

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761012

Alexandre Antunes, Alban Laflaquière, A. Cangelosi

{"title":"Solving Bidirectional Tasks using MTRNN","authors":"Alexandre Antunes, Alban Laflaquière, A. Cangelosi","doi":"10.1109/DEVLRN.2018.8761012","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761012","url":null,"abstract":"In this paper we study the learning of bidirectional tasks in a Recurrent Neural Network (RNN). Most of such models deal with a flow of information in only one direction, either generating outputs or encoding inputs; However, using a single network to do both tasks simultaneously would be more efficient and biologically plausible. We will be using a Multiple Timescales Recurrent Neural Network (MTRNN) to solve these tasks. The network proves capable of dealing with this bidirectional-flow of information simply by training in both directions, with outputs becoming inputs and vice-versa. We showcase this behaviour on two tasks, using the same network. the first is a sentence learning task, akin to a classification problem. The second task is a motor trajectory learning task, akin to a regression problem. The data used in these tasks has been generated through an iCub robot. We present the results of these experiments and show that this model maintains its properties for the bidirectional tasks. We discuss possible future implementations using this ability to solve more complex scenarios such as action and language grounding.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"257O 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128015215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Detecting Features of Tools, Objects, and Actions from Effects in a Robot using Deep Learning 利用深度学习从机器人的效果中检测工具、对象和动作的特征

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761029

Namiko Saito, Kitae Kim, Shingo Murata, T. Ogata, S. Sugano

引用次数: 3

Transfer Learning of Complex Motor Skills on the Humanoid Robot Affetto 仿人机器人Affetto复杂运动技能的迁移学习

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761031

Alexander Schulz, J. Queißer, H. Ishihara, M. Asada

引用次数: 1

Predictive Models for Robot Ego-Noise Learning and Imitation 机器人自我噪声学习与模仿的预测模型

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761017

Antonio Pico Villalpando, G. Schillaci, V. Hafner

{"title":"Predictive Models for Robot Ego-Noise Learning and Imitation","authors":"Antonio Pico Villalpando, G. Schillaci, V. Hafner","doi":"10.1109/DEVLRN.2018.8761017","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761017","url":null,"abstract":"We investigate predictive models for robot ego-noise learning and imitation. In particular, we present a framework based on internal models—such as forward and inverse models—that allow a robot to learn how its movements sound like, and to communicate actions to perform to other robots through auditory means. We adopt a developmental approach in the learning of such models, where training sensorimotor data is gathered through self-exploration behaviours. In a simulated experiment presented here, a robot generates specific auditory features from an intended sequence of actions and communicates them for reproduction to another robot, which consequently decodes them into motor commands, using the knowledge of its own motor system. As to the current state, this paper presents an experiment where a robot reproduces auditory sequences previously generated by itself. The presented experiment demonstrates the potentials of the proposed architecture for robot ego-noise learning and for robot communication and imitation through natural means, such as audition. Future work will include situations where different agents use models that are trained with—and thus are specific to—their own self-generated sensorimotor data.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116827280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Microsaccades for asynchronous feature extraction with spiking networks 基于脉冲网络的异步特征提取微跳图

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761007

Jacques Kaiser, Gerd Lindner, J. C. V. Tieck, Martin Schulze, M. Hoff, A. Rönnau, R. Dillmann

{"title":"Microsaccades for asynchronous feature extraction with spiking networks","authors":"Jacques Kaiser, Gerd Lindner, J. C. V. Tieck, Martin Schulze, M. Hoff, A. Rönnau, R. Dillmann","doi":"10.1109/DEVLRN.2018.8761007","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761007","url":null,"abstract":"While extracting spatial features from images has been studied for decades, extracting spatio-temporal features from event streams is still a young field of research. A particularity of event streams is that the same network architecture can be used for recognition of static objects or motions. However, it is not clear what features provide a good abstraction and in what scenario. In this paper, we evaluate the quality of the features of a spiking HMAX architecture by computing classification performance before and after each layer. We demonstrate the abstraction capability of classical edge features, as were found in the V1 area of the visual cortex, combined with fixational eye movements. Specifically, our performance on N-Caltech101 dataset outperforms previously reported $F_{1}$ score on Caltech101, with a similar architecture but without a STDP learning layer. However, we show that the same edge features do not manage to abstract motions observed with a static DVS from the DvsGesture dataset. Additionally, we show that liquid state machines are a promising computational model for the classification of DVS data with temporal dynamics. This paper is a step forward towards understanding and reproducing biological vision.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134141429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Cooperative Control of An Ankle Rehabilitation Robot Based on Human Intention 基于人意向的踝关节康复机器人协同控制

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761006

Qingsong Ai, Lei Wang, Kun Chen, Anqi Chen, Jiwei Hu, Yilin Fang, Quan Liu, Zude Zhou

{"title":"Cooperative Control of An Ankle Rehabilitation Robot Based on Human Intention","authors":"Qingsong Ai, Lei Wang, Kun Chen, Anqi Chen, Jiwei Hu, Yilin Fang, Quan Liu, Zude Zhou","doi":"10.1109/DEVLRN.2018.8761006","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761006","url":null,"abstract":"Motor imagery electroencephalogram (EEG) is a kind of brain signal induced by subjective consciousness. Relevant studies in the field of sports rehabilitation show that motor imagery training can promote the recovery of damaged nerves and the reconstruction of motor nerve pathways. This paper proposes a human-brain cooperative control strategy of a pneumatic muscle-driven ankle rehabilitation robot based on motor imagery EEG. Robots provide assisted rehabilitation training for patients with impaired neural transmission but with movement intentions. The brain network algorithm is used to select the optimal channels for the motor imagery signal, and the common spatial pattern (CSP) method is combined with the time-frequency analysis method local characteristic-scale decomposition (LCD) to extract the time-frequency information. Finally, the classification is processed by the spectral regression discriminant analysis (SRDA) classifier. In addition, two rehabilitation training modes are designed, namely, synchronous rehabilitation training and asynchronous rehabilitation training. The experimental results prove that a brain intention driven human robot cooperative control method is realized to complete an ankle rehabilitation training task effectively.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128908992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Efficient Reward-Based Learning through Body Representation in a Spiking Neural Network 尖峰神经网络中基于身体表征的有效奖励学习

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761011

Yuji Kawai, Tomohiro Takimoto, Jihoon Park, M. Asada

{"title":"Efficient Reward-Based Learning through Body Representation in a Spiking Neural Network","authors":"Yuji Kawai, Tomohiro Takimoto, Jihoon Park, M. Asada","doi":"10.1109/DEVLRN.2018.8761011","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761011","url":null,"abstract":"Brain-body interactions guide the development of behavioral and cognitive functions. Sensory signals during behavior are relayed to the brain and evoke neural activity. This feedback is important for the organization of neural networks via neural plasticity, which in turn facilitates the generation of motor commands for new behaviors. In this study, we investigated how brain-body interactions develop and affect reward-based learning. We constructed a spiking neural network (SNN) model for the reward-based learning of canonical babbling, i.e., combination of a vowel and consonant. Motor commands to a vocal simulator were generated by SNN output and auditory signals representing the vocalized sound were fed back into the SNN. Synaptic weights in the SNN were updated using spike-timing-dependent plasticity (STDP). Connections from the SNN to the vocal simulator were modulated based on reward signals in terms of saliency of the vocalized sound. Our results showed that, under auditory feedback, STDP enabled the model to rapidly acquire babbling-like vocalization. We found that some neurons in the SNN were more highly activated during vocalization of a consonant than during other sounds. That is, neural dynamics in the SNN adapted to task-related articulator movements. Accordingly, body representation in the SNN facilitated brain-body interaction and accelerated the acquisition of babbling behavior.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114308512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Who Can Benefit from Robots? Effects of Individual Differences in Robot-Assisted Language Learning 谁能从机器人中受益?机器人辅助语言学习中个体差异的影响

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761028

Junko Kanero, Idil Franko, Cansu Oranç, Orhun Ulusahin, Sümeyye Koskulu, Zeynep Adıgüzel, A. Küntay, T. Göksun

引用次数: 6

Adaptive and Variational Continuous Time Recurrent Neural Networks 自适应和变分连续时间递归神经网络

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761019

Stefan Heinrich, Tayfun Alpay, S. Wermter

{"title":"Adaptive and Variational Continuous Time Recurrent Neural Networks","authors":"Stefan Heinrich, Tayfun Alpay, S. Wermter","doi":"10.1109/DEVLRN.2018.8761019","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761019","url":null,"abstract":"In developmental robotics, we model cognitive processes, such as body motion or language processing, and study them in natural real-world conditions. Naturally, these sequential processes inherently occur on different continuous timescales. Similar as our brain can cope with them by hierarchical abstraction and coupling of different processing modes, computational recurrent neural models need to be capable of adapting to temporally different characteristics of sensorimotor information. In this paper, we propose adaptive and variational mechanisms that can tune the timescales in Continuous Time Recurrent Neural Networks (CTRNNs) to the characteristics of the data. We study these mechanisms in both synthetic and natural sequential tasks to contribute to a deeper understanding of how the networks develop multiple timescales and represent inherent periodicities and fluctuations. Our findings include that our Adaptive CTRNN (ACTRNN) model self-organises timescales towards both representing short-term dependencies and modulating representations based on long-term dependencies during end-to-end learning.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125524417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4