Improved Interpretability and Generalisation for Deep Learning
نویسنده
چکیده
منابع مشابه
Deep Neural Networks with Massive Learned Knowledge
Regulating deep neural networks (DNNs) with human structured knowledge has shown to be of great benefit for improved accuracy and interpretability. We develop a general framework that enables learning knowledge and its confidence jointly with the DNNs, so that the vast amount of fuzzy knowledge can be incorporated and automatically optimized with little manual efforts. We apply the framework to...
متن کاملFeature Graph Architectures
In this article we propose feature graph architectures (FGA), which are deep learning systems employing a structured initialisation and training method based on a feature graph which facilitates improved generalisation performance compared with a standard shallow architecture. The goal is to explore alternative perspectives on the problem of deep network training. We evaluate FGA performance fo...
متن کاملVisual Interpretability forDeepLearning
This paper reviews recent studies in emerging directions of understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, the interpretability is always an Achilles' heel of deep neural networks. At present, deep neural networks obtain a h...
متن کاملTransferring Rich Deep Features for Facial Beauty Prediction
Feature extraction plays a significant part in computer vision tasks. In this paper, we propose a method which transfers rich deep features from a pretrained model on face verification task and feeds the features into Bayesian ridge regression algorithm for facial beauty prediction. We leverage the deep neural networks that extracts more abstract features from stacked layers. Through simple but...
متن کاملThinking Fast and Slow with Deep Learning and Tree Search
Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (EXIT), a novel reinforcement learning algorithm which decomposes the problem into separate planning and generalisation tasks. Planning new policies is performed by tree sea...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017