Long Short-Term Memory in Recognizing Behavior Sequences on Humanoid Robot.

In order for robots to learn more complex behaviors, recognizing primitive behaviors plays a fundamental role. Research has shown that the recognition of primitive behaviors such as basic gestures enables robots to learn more complex behaviors as combinations of these simple, primitive behaviors. The focus of this study is to investigate the tolerance of neural network models to noisy inputs. We compare and evaluate several neural network architectures including the multilayer perceptron (MLP), time-delay neural network (TDNN), recurrent neural network (RNN) and the Long Short-Term Memory (LSTM). We show that the LSTM is superior to other models in terms of its robustness noisy inputs subjected to Gaussian noise.

[1]  Rich Caruana,et al.  Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping , 2000, NIPS.

[2]  Martin A. Riedmiller,et al.  Advanced supervised learning in multi-layer perceptrons — From backpropagation to adaptive learning algorithms , 1994 .

[3]  Khairul Salleh Mohamed Sahari,et al.  Multiple sequence behavior recognition on humanoid robot using long short-term memory (LSTM) , 2014, 2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA).

[4]  Min Qi,et al.  Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging , 2001, IEEE Trans. Neural Networks.

[5]  Jan Peters,et al.  Reinforcement learning in robotics: A survey , 2013, Int. J. Robotics Res..

[6]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[7]  Yuki Suga,et al.  Multimodal integration learning of object manipulation behaviors using deep neural networks , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Erik Billing,et al.  Cognition Rehearsed : Recognition and Reproduction of Demonstrated Behavior , 2012 .

[9]  Martin A. Riedmiller,et al.  RPROP - A Fast Adaptive Learning Algorithm , 1992 .

[10]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[11]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[12]  Anders Krogh,et al.  A Simple Weight Decay Can Improve Generalization , 1991, NIPS.

[13]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[14]  Y. Yao,et al.  On Early Stopping in Gradient Descent Learning , 2007 .

[15]  Gerhard Lakemeyer,et al.  Cognitive Robotics , 2008, Handbook of Knowledge Representation.

[16]  Lutz Prechelt,et al.  Early Stopping-But When? , 1996, Neural Networks: Tricks of the Trade.

[17]  Yuki Suga,et al.  Multimodal integration learning of robot behavior using deep neural networks , 2014, Robotics Auton. Syst..