In this paper, we investigate the problem of overfitting in deep reinforcement learning.
Continual learning has received a great deal of attention recently with several approaches being proposed.
We propose a deep collaborative weight-based classification (DeepCWC) method to resolve this problem, by providing a novel option to fully take advantage of deep features in classic machine learning.
We have developed convolutional neural networks (CNN) for a facial expression recognition task.
We propose a smooth kernel regularizer that encourages spatial correlations in convolution kernel weights.
In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model architecture.
There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.
Ranked #13 on Image Generation on CIFAR-10 (Inception score metric)
This paper identifies a problem with the usual procedure for L2-regularization parameter estimation in a domain adaptation setting.