No abstract

No abstract

In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs. We validate our models by creating a real-time vision system which accomplishes the tasks of face detection, gender classification and emotion classification simultaneously in one blended step using our proposed CNN architecture. After presenting the details of the training procedure setup we proceed to evaluate on standard benchmark sets. We report accuracies of 96% in the IMDB gender dataset and 66% in the FER-2013 emotion dataset. Along with this we also introduced the very recent real-time enabled guided backpropagation visualization technique. Guided back-propagation uncovers the dynamics of the weight changes and evaluates the learned features. We argue that the careful implementation of modern CNN architectures, the use of the current regularization methods and the visualization of previously hidden features are necessary in order to reduce the gap between slow performances and real-time architectures. Our system has been validated by its deployment on a Care-O-bot 3 robot used during RoboCup@Home competitions. All our code, demos and pretrained architectures have been released under an open-source license in our public repository.

No abstract

Abstract. Applications of recurrent neural networks (RNNs) tend to be rare because training is difficult. A recent theoretical breakthrough [Jae01b] called Echo State Networks (ESNs) has made RNN training easy and fast and makes RNNs a versatile tool for many problems. The key idea is training the output weights only of an otherwise topologically unrestricted but contractive network. After outlining the mathematical basics, we apply ESNs to two examples namely to the generation of a dynamical model for a differential drive robot using supervised learning and secondly to the training of a respective motor controller.