Figure 1: Lifelong learning of conditional image generation. Traditional training methods suffer from catastrophic forgetting: when we add new tasks, the network forgets how to perform previous tasks. Our Lifelong GAN is a generic framework for conditional image generation that applies to various types of conditional inputs (e.g. labels and images). AbstractLifelong learning is challenging for deep neural networks due to their susceptibility to catastrophic forgetting. Catastrophic forgetting occurs when a trained network is not able to maintain its ability to accomplish previously learned tasks when it is trained to perform new tasks. We study the problem of lifelong learning for generative models, extending a trained network to new conditional generation tasks without forgetting previous tasks, while assuming access to the training data for the current task only. In contrast to state-of-the-art memory replay based approaches which are limited to label-conditioned image generation tasks, a more generic framework for continual learning of generative models under different conditional image generation settings is proposed in this paper. Lifelong GAN employs knowledge distillation to transfer learned knowledge from previous networks to the new network. This makes it possible to perform image-conditioned generation tasks in a lifelong learning setting. We validate Lifelong GAN for both image-conditioned and label-conditioned generation tasks, and provide qualitative and quantitative results to show the generality and effectiveness of our method. * Equal Contribution

No abstract

No abstract

No abstract

This is a repository copy of A stacked auto-encoder based partial adversarial domain adaptation model for intelligent fault diagnosis of rotating machines.

We investigate two deep learning architectures reported to have superior performance in ASR over the conventional GMM system, with respect to automatic speech scoring. We use an approximately 800-hour large-vocabulary non-native spontaneous English corpus to build three ASR systems. One system is in GMM, and two are in deep learning architectures -namely, DNN and Tandem with bottleneck features. The evaluation results show that the both deep learning systems significantly outperform the GMM ASR. These ASR systems are used as the front-end in building an automated speech scoring system. To examine the effectiveness of the deep learning ASR systems for automated scoring, another non-native spontaneous speech corpus is used to train and evaluate the scoring models. Using deep learning architectures, ASR accuracies drop significantly on the scoring corpus, whereas the performance of the scoring systems get closer to human raters, and consistently better than the GMM one. Compared to the DNN ASR, the Tandem performs slightly better on the scoring speech while it is a little less accurate on the ASR evaluation dataset. Furthermore, given the results of the improved scoring performance while using fewer scoring features, the Tandem system shows more robustness for scoring task than the DNN one.Index Termsautomatic speech scoring, non-native spontaneous speech, automatic speech recognition, deep neural network, bottleneck features

No abstract

Transcranial sonography (TCS) is a new tool for the diagnosis of Parkinson's disease (PD) at a very early state. The TCS image of mesencephalon shows a distinct hyperechogenic pattern in about 90% PD patients. This pattern is usually manually segmented and the substantia nigra (SN) region can be used as an early PD indicator. However this method is based on manual evaluation of examined images. The extraction of multiple features from TCS images characterizing the half mesencephalon morphology and structure can be used to validate the observer-independent PD indicator. We propose hybrid feature extraction methods which includes statistical, geometrical and texture features for the early PD risk assessment. These features are tested with support vector machines (SVMs). Furthermore five features are selected with the sequential feature selection methods. The results show that the correct rate of the classification with these five features is reaching 96%.