標題: Titlebook: Artificial Neural Networks and Machine Learning – ICANN 2017; 26th International C Alessandra Lintas,Stefano Rovetta,Alessandro E.P. Confe [打印本頁] 作者: Spouse 時間: 2025-3-21 16:41
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017影響因子(影響力)
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017影響因子(影響力)學科排名
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017網(wǎng)絡公開度
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017網(wǎng)絡公開度學科排名
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017被引頻次
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017被引頻次學科排名
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017年度引用
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017年度引用學科排名
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017讀者反饋
書目名稱Artificial Neural Networks and Machine Learning – ICANN 2017讀者反饋學科排名
作者: LUCY 時間: 2025-3-21 20:43
Robot Localization and Orientation Detection Based on Place Cells and Head-Direction Cells作者: 放逐 時間: 2025-3-22 02:40
Artificial Neural Networks and Machine Learning – ICANN 201726th International C作者: WAX 時間: 2025-3-22 07:06
0302-9743 g and Medical Applications; Advances in Machine Learning.. There are 63 short paper abstracts that are included in the back matter of the volume..978-3-319-68599-1978-3-319-68600-4Series ISSN 0302-9743 Series E-ISSN 1611-3349 作者: 連詞 時間: 2025-3-22 10:43
Kognitiv-physiologischer Forschungsansatzimulation results show that our approach achieves significantly better performance compared with two existing approaches in terms of load balancing, user payoff and the overall bandwidth utilization efficiency.作者: Obituary 時間: 2025-3-22 15:57 作者: 遺產(chǎn) 時間: 2025-3-22 20:35
https://doi.org/10.1007/978-3-322-91075-2e being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the 作者: synovitis 時間: 2025-3-22 22:12 作者: 尊敬 時間: 2025-3-23 02:57
https://doi.org/10.1007/978-3-322-90299-3w that concurrent action execution and action perception influence each other. We have developed a physiologically-inspired neural model that accounts for the neural encoding of perceived actions and motor plans, and their interactions. The core of the model is a set of coupled neural fields that re作者: Extort 時間: 2025-3-23 07:14 作者: 簡略 時間: 2025-3-23 12:44
https://doi.org/10.1007/978-3-322-90299-3nformation on location was provided, and no maps were constructed. The model comprised a deep autoencoder and a recurrent neural network. The model was demonstrated to (1) learn to correctly label areas of different shapes and sizes, (2) be capable of adapting to changes in room shape and rearrangem作者: aphasia 時間: 2025-3-23 14:39 作者: 發(fā)誓放棄 時間: 2025-3-23 19:06
https://doi.org/10.1007/978-3-322-90299-3(SOMPAM). In this method, patterns corresponding to the pairs of observation and action are memorized to the SOMPAM, and the brief degree is set to value of the rule. In this research robot learns with the aim of acquiring an action rule that can reach the goal point from the start point with as few作者: cocoon 時間: 2025-3-23 22:27
https://doi.org/10.1007/978-3-322-90299-3nit capable to perform on-line analysis for closed-loop control. Here, we present an ultra-compact and low-power system able to acquire from 32 channels and stimulate independently using both current and voltage. The system has been validated . for rats in the recording of spontaneous and evoked pot作者: osteoclasts 時間: 2025-3-24 04:57 作者: 截斷 時間: 2025-3-24 09:03
https://doi.org/10.1007/978-3-322-90445-4telligence argue that sensorimotor prediction is a fundamental building block of cognition. In this paper, we learn the sensorimotor prediction on data captured by a mobile robot equipped with distance sensors. We show that Neural Networks can learn the sensorimotor regularities and perform sensorim作者: 不近人情 時間: 2025-3-24 10:54 作者: Aggregate 時間: 2025-3-24 18:15 作者: 襲擊 時間: 2025-3-24 19:40 作者: 要塞 時間: 2025-3-25 01:47 作者: 共同給與 時間: 2025-3-25 03:58 作者: extemporaneous 時間: 2025-3-25 10:42
Artificial Neural Networks and Machine Learning – ICANN 2017978-3-319-68600-4Series ISSN 0302-9743 Series E-ISSN 1611-3349 作者: 啜泣 時間: 2025-3-25 11:38 作者: 拒絕 時間: 2025-3-25 18:45 作者: 膝蓋 時間: 2025-3-25 23:02 作者: 好色 時間: 2025-3-26 03:21 作者: Absenteeism 時間: 2025-3-26 05:37
Semi-supervised Phoneme Recognition with Recurrent Ladder Networkse being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the 作者: 悅耳 時間: 2025-3-26 10:13
Mixing Actual and Predicted Sensory States Based on Uncertainty Estimation for Flexible and Robust Rbot behavior. We employ the so-called stochastic continuous-time RNN (S-CTRNN), which can learn to predict the mean and variance (or uncertainty) of subsequent sensorimotor information. Our proposed method uses this estimated uncertainty to determine a mixture ratio for combining actual and predicte作者: 掃興 時間: 2025-3-26 16:23 作者: 左右連貫 時間: 2025-3-26 19:43
Neural End-to-End Self-learning of Visuomotor Skills by Environment Interactionex environments, generating suitable training data is time-consuming and depends on the availability of accurate robot models. Deep reinforcement learning alleviates this challenge by letting robots learn in an unsupervised manner through trial and error at the cost of long training times. In contra作者: oxidant 時間: 2025-3-26 21:45 作者: dialect 時間: 2025-3-27 02:37
Towards Grasping with Spiking Neural Networks for Anthropomorphic Robot Handsdify them during execution based on the shape and the intended interaction with objects. We present a hierarchical spiking neural network with a biologically inspired architecture for representing different grasp motions. We demonstrate the ability of our network to learn from human demonstration us作者: HAUNT 時間: 2025-3-27 09:11 作者: peritonitis 時間: 2025-3-27 13:16 作者: 暴發(fā)戶 時間: 2025-3-27 15:27 作者: QUAIL 時間: 2025-3-27 20:40
Sensorimotor Prediction with Neural Networks on Continuous Spacestelligence argue that sensorimotor prediction is a fundamental building block of cognition. In this paper, we learn the sensorimotor prediction on data captured by a mobile robot equipped with distance sensors. We show that Neural Networks can learn the sensorimotor regularities and perform sensorim作者: Enervate 時間: 2025-3-28 01:12
Classifying Bio-Inspired Model of Point-Light Human Motion Using Echo State Networksan action descriptor. The Echo State Network (ESN) which also has a biological plausibility is chosen for classification. We demonstrate the efficiency and robustness of applying the proposed feature extraction technique with ESN by constraining the test data based on arbitrary untrained viewpoints,作者: 碎石 時間: 2025-3-28 03:00
A Prediction and Learning Based Approach to Network Selection in Dynamic Environmentsemented in static network environments while cannot handle unpredictable dynamics in practice. In this paper, we propose a prediction and learning based approach, which considers both the fluctuation of radio resource and the variation of user demand. The network selection scenario is modeled as a m作者: 不幸的人 時間: 2025-3-28 06:29 作者: 拋射物 時間: 2025-3-28 11:22
Learning Distance-Behavioural Preferences Using a Single Sensor in a Spiking Neural?Networkle non-calibrated sensor in combination with neural elements could provide flexibility through learning, to effectively cope with changing environments. The objective of this study was to design an adaptive system with the potential capability of learning behavioural preferences in relation to disti作者: 滲透 時間: 2025-3-28 15:57
Towards an Accurate Identification of Pyloric Neuron Activity with VSDin is an important technique to supplement electrophysiological recordings. However, utilising the technique to identify pyloric neurons directly is a computationally exacting task that requires the development of sophisticated signal processing procedures to analyse the tri-phasic pyloric patterns g作者: Suggestions 時間: 2025-3-28 21:40 作者: 線 時間: 2025-3-29 00:42
https://doi.org/10.1007/978-3-322-91075-2ensory-independent task requires the robot to ignore irrelevant sensory information. Experimental results demonstrate that a robot controlled by our proposed method exhibits flexible and robust behavior, which results from dynamic modulation of the network input on the basis of the estimated uncertainty of actual sensory states.作者: 開始從未 時間: 2025-3-29 04:22 作者: subacute 時間: 2025-3-29 08:06
Mixing Actual and Predicted Sensory States Based on Uncertainty Estimation for Flexible and Robust Rensory-independent task requires the robot to ignore irrelevant sensory information. Experimental results demonstrate that a robot controlled by our proposed method exhibits flexible and robust behavior, which results from dynamic modulation of the network input on the basis of the estimated uncertainty of actual sensory states.作者: enlist 時間: 2025-3-29 12:49 作者: WAG 時間: 2025-3-29 18:38
Conference proceedings 2017, held in Alghero, Italy, in September 2017...The 128 full papers included in this volume were carefully reviewed and selected from 270 submissions. They were organized in topical sections named: From Perception to Action; From Neurons to Networks; Brain Imaging; Recurrent Neural Networks; Neuromorp作者: 親愛 時間: 2025-3-29 20:32
https://doi.org/10.1007/978-3-322-91075-2model is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.作者: Kaleidoscope 時間: 2025-3-30 01:52
https://doi.org/10.1007/978-3-322-90299-3ent of items in the room, and (3) attribute different labels to the same area, when approached from different angles. Analysis of the internal representations of the model showed that a topological structure corresponding to the room structure was self-organized as the trajectory of the internal activations of the network.作者: 灰姑娘 時間: 2025-3-30 05:06
https://doi.org/10.1007/978-3-322-90299-3ing synaptic plasticity on two different exemplary grasp types (pinch and cylinder). We evaluate the performance of the network in simulation and on a real anthropomorphic robotic hand. The network exposes the ability of learning finger coordination and synergies between joints that can be used for grasping.作者: faction 時間: 2025-3-30 11:24 作者: Free-Radical 時間: 2025-3-30 13:46
Korrespondenzen von Medien und Gewalt in combination with unseen subjects under the following conditions: (i) lower sub-sampling frame rates to simulate data sequence loss, (ii) remove key points to simulate occlusion, and (iii) include untrained movements such as ..作者: 分解 時間: 2025-3-30 18:29
Semi-supervised Phoneme Recognition with Recurrent Ladder Networksmodel is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.作者: AMBI 時間: 2025-3-30 21:30
Learning of Labeling Room Space for Mobile Robots Based on Visual Motor Experienceent of items in the room, and (3) attribute different labels to the same area, when approached from different angles. Analysis of the internal representations of the model showed that a topological structure corresponding to the room structure was self-organized as the trajectory of the internal activations of the network.作者: 倔強一點 時間: 2025-3-31 03:11 作者: inhibit 時間: 2025-3-31 06:37
An Ultra-Compact Low-Powered Closed-Loop Device for Control of the Neuromuscular Systementials and peripheral nerve stimulation, and it was tested to reproduce the muscular activity involved in gait. This device has potential application in long-term clinical therapies for the restoration of limb control and it can become a development platform for closed loop algorithms in neuromuscular interfaces.作者: 剛開始 時間: 2025-3-31 10:58
Classifying Bio-Inspired Model of Point-Light Human Motion Using Echo State Networks in combination with unseen subjects under the following conditions: (i) lower sub-sampling frame rates to simulate data sequence loss, (ii) remove key points to simulate occlusion, and (iii) include untrained movements such as ..作者: 無價值 時間: 2025-3-31 16:59 作者: 谷物 時間: 2025-3-31 19:59
https://doi.org/10.1007/978-3-322-90445-4a captured by a mobile robot equipped with distance sensors. We show that Neural Networks can learn the sensorimotor regularities and perform sensorimotor prediction on continuous sensor and motor spaces.作者: 柔美流暢 時間: 2025-3-31 23:05
Aporien der Mediengewaltforschungcomputationally exacting task that requires the development of sophisticated signal processing procedures to analyse the tri-phasic pyloric patterns generated by these neurons. This paper presents our work towards commissioning such procedures. The results achieved to date are most encouraging.作者: 過分 時間: 2025-4-1 05:11 作者: MEET 時間: 2025-4-1 08:54
Towards an Accurate Identification of Pyloric Neuron Activity with VSDicomputationally exacting task that requires the development of sophisticated signal processing procedures to analyse the tri-phasic pyloric patterns generated by these neurons. This paper presents our work towards commissioning such procedures. The results achieved to date are most encouraging.作者: refine 時間: 2025-4-1 12:02 作者: phase-2-enzyme 時間: 2025-4-1 15:37
https://doi.org/10.1007/978-3-322-90299-3 interaction with the environment based on initial motor abilities. Supervised end-to-end learning of visuomotor skills is realized with a deep convolutional neural architecture that combines two important subtasks of grasping: object localization and inverse kinematics.作者: Misnomer 時間: 2025-4-1 20:32
https://doi.org/10.1007/978-3-322-90299-3as observation. In the simulation environment reproducing the experimental environment, we confirmed that the learning converged to a state where it can reach the goal while avoiding obstacles with the minimum steps. Moreover, even in the real environment, it was confirmed that the robot can reach the goal while avoiding obstacles.
