Lifelong learning of human actions with deep neural network self-organization

Citations Over TimeTop 10% of 2017 papers

Abstract

Lifelong learning is fundamental in autonomous robotics for the acquisition and fine-tuning of knowledge through experience. However, conventional deep neural models for action recognition from videos do not account for lifelong learning but rather learn a batch of training data with a predefined number of action classes and samples. Thus, there is the need to develop learning systems with the ability to incrementally process available perceptual cues and to adapt their responses over time. We propose a self-organizing neural architecture for incrementally learning to classify human actions from video sequences. The architecture comprises growing self-organizing networks equipped with recurrent neurons for processing time-varying patterns. We use a set of hierarchically arranged recurrent networks for the unsupervised learning of action representations with increasingly large spatiotemporal receptive fields. Lifelong learning is achieved in terms of prediction-driven neural dynamics in which the growth and the adaptation of the recurrent networks are driven by their capability to reconstruct temporally ordered input sequences. Experimental results on a classification task using two action benchmark datasets show that our model is competitive with state-of-the-art methods for batch learning also when a significant number of sample labels are missing or corrupted during training sessions. Additional experiments show the ability of our model to adapt to non-stationary input avoiding catastrophic interference.

Related Papers

• → Centroid neural network for unsupervised competitive learning(2000)90 cited
• → Hebbian learning and the LMS algorithm(2016)9 cited
• → Development of a neural network algorithm for unsupervised competitive learning(2002)5 cited
• → TInMANN - The Integer Markovian Artificial Neural Network for Performing Competitive and Kohonen Learning(1995)1 cited
• → An unsupervised learning rule for the pulsed neuron model - the vector quantization of the auditory temporal signals(2000)1 cited