Interpretable convolutional neural networks via feedforward design
نویسندگان
چکیده
منابع مشابه
Interpretable Deep Convolutional Neural Networks via Meta-learning
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model’s outputs. The recent movement for “algorithmic fairness” also stipulates explainability, and therefore interpretability of learning models. And yet the most successful contemporary Machine Learning approaches, the Deep Neural Networks, produce models that are highly non-...
متن کاملFlattened Convolutional Neural Networks for Feedforward Acceleration
We present flattened convolutional neural networks that are designed for fast feedforward execution. The redundancy of the parameters, especially weights of the convolutional filters in convolutional neural networks has been extensively studied and different heuristics have been proposed to construct a low rank basis of the filters after training. In this work, we train flattened networks that ...
متن کاملGraph Convolutional Neural Networks via Scattering
We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We show that under certain conditions, any feature generated by such a network is approximately invariant to permutations and stable to graph manipulations. Numerical results demonstrate competitive performance on relevant datasets.
متن کاملCrater Detection via Convolutional Neural Networks
Joseph Paul Cohen, Henry Z. Lo, Tingting Lu, and Wei Ding at the University of Massachusetts Boston ({joecohen, henryzlo, ding}@cs.umb.edu, [email protected]) Introduction Craters are among the most studied geomorphic features in the Solar System because they yield important information about the past and present geological processes and provide information about the relative ages of obser...
متن کاملPersonalized Citation Recommendation via Convolutional Neural Networks
Automatic citation recommendation based on citation context, together with consideration of users’ preference and writing patterns is an emerging research topic. In this paper, we propose a novel personalized convolutional neural networks (p-CNN) discriminatively trained by maximizing the conditional likelihood of the cited documents given a citation context. The proposed model not only nicely ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Visual Communication and Image Representation
سال: 2019
ISSN: 1047-3203
DOI: 10.1016/j.jvcir.2019.03.010