情報処理学会 第81回全国大会講演要旨
5C-01
ディープニューラルネットワークの継続的な学習
Deep Neural Networks (DNNs) have shown promising performance in various kinds of applications. However, different from human brain, a well-trained DNN is not capable of remembering old classes when learning new classes, which is called catastrophic forgetting of neural networks.
In this work, one approach based on feature extraction for DNNs to overcome the forgetting problem is proposed. It tries to maintain the knowledge of old classes by building and storing average feature vectors of the training data seen so far. Testing with MNIST and CIFAR dataset, we prove that our approach can efficiently decrease the cost for DNNs' continual learning of new classes as there is no need to retrain all the old classes.
In this work, one approach based on feature extraction for DNNs to overcome the forgetting problem is proposed. It tries to maintain the knowledge of old classes by building and storing average feature vectors of the training data seen so far. Testing with MNIST and CIFAR dataset, we prove that our approach can efficiently decrease the cost for DNNs' continual learning of new classes as there is no need to retrain all the old classes.
