The past few years have witnessed growth in the size and computational requirements for training deep convolutional neural networks. Current approaches parallelize the training process onto multiple devices by applying a single parallelization strategy (e.g., data or model parallelism) to all layers in a network. Although easy to reason about, this design results in suboptimal runtime performan...

We present a unifying approach to multiple testing procedures for sequential (or streaming) data by giving sufficient conditions for a sequential multiple testing procedure to control the familywise error rate (FWER). Together we call these conditions a "rejection principle for sequential tests," which we then apply to some existing sequential multiple testing procedures to give simplified unde...

Layer-wise relevance propagation is a framework which allows to decompose the prediction of a deep neural network computed over a sample, e.g. an image, down to relevance scores for the single input dimensions of the sample such as subpixels of an image. While this approach can be applied directly to generalized linear mappings, product type non-linearities are not covered. This paper proposes ...

We propose algorithms based on an optimisation method for inverse multislice ptychography in, e.g. electron microscopy. The is widely used to model the interaction between relativistic electrons and thick specimens. Since only intensity of diffraction patterns can be recorded, challenge in applying uniquely reconstruct electrostatic potential each slice up some ambiguities. In this conceptual s...

We present the application of layer-wise relevance propagation to several deep neural networks such as the BVLC reference neural net and googlenet trained on ImageNet and MIT Places datasets. Layerwise relevance propagation is a method to compute scores for image pixels and image regions denoting the impact of the particular image region on the prediction of the classifier for one particular te...

On Layer-Wise Representations in Deep Neural Networks It is well-known that deep neural networks are forming an efficient internal representation of the learning problem. However, it is unclear how this efficient representation is distributed layer-wise, and how it arises from learning. In this thesis, we develop a kernel-based analysis for deep networks that quantifies the representation at ea...

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples of different complexities. For example, if a training sample has already been correctly classified at a specific layer with high confidence, we argue that it ...