Inthis supplemental material, wefirst present thedetailed networkarchitecture andparameters of the proposed approach in Sec. A. We further provide more analysis of the proposed method and ablation studies in Sec. B. Section C shows some qualitative results for potential applications of the proposed approach on medical imaging and imaging in astronomy. Figure 6: Illustration of learned deep features.(a) The blurry input and ground truth are shown in Figure 1(a)-(b). However, on may actually wonder whether the feature extraction network acts as a denoiser, leading to the observed robustness of the proposed method to various noise levels.

In this paper we consider the case of generativemodels. In particular,we investigate generativeadversarialnetworks (GANs) in the task of learning new categories in a sequential fashion.

Scaling model capacity has been vital in the success of deep learning.

Time series with non-uniform intervals occur in many applications, and are difficulttomodel usingstandard recurrent neural networks(RNNs).

Conventional models prepare a large embedding matrix whose size depends on the vocabulary size. Therefore, storing these models in memory and disk storage is costly.

Neural Information Processing Systems http://nips.cc/

Whenthe smooth, weobtain: Problem (3.6) ourand Assumption 2.2 holds.

The problem of extracting auseful interpretation from an image may be simplified byimagesegmentation, i.e., by partitioning such image into regions associated to separate objects.

In this work, we showthat this "lazy training" phenomenon isnot specific tooverparameterized neural networks, and is due to a choice of scaling, often implicit, that makes the model behave as its linearization around the initialization, thus yielding amodel equivalenttolearning withpositive-definite kernels.

How would you describe why the image in Figure 1 looks like a clay colored sparrow? Perhaps the bird's head and wing bars look like those of a prototypical clay colored sparrow. When we describe how we classify images, we might focus on parts of the image and compare them with prototypical parts of images from a given class. This method of reasoning is commonly used in difficult identification tasks: e.g., radiologists compare suspected tumors in X-ray scans with prototypical tumor images for diagnosis of cancer [13].