Publication: Long short-term memory in recognizing behavior sequences on humanoid robot.
Date
2018
Authors
Neoh D.
Mohamed Sahari K.S.
Loo C.K.
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers Inc.
Abstract
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. � 2018 IEEE.
Description
Anthropomorphic robots; Behavioral research; Brain; Complex networks; Deep learning; Gaussian noise (electronic); Intelligent computing; Intelligent systems; Network architecture; Soft computing; Behavior recognition; Behavior sequences; Humanoid; LSTM; Multi layer perceptron; Neural network model; Recurrent neural network (RNN); Time delay neural networks; Long short-term memory