English
Related papers

Related papers: Complex Critical Points of Deep Linear Neural Netw…

200 papers

Multipliers are the most space and power-hungry arithmetic operators of the digital implementation of deep neural networks. We train a set of state-of-the-art neural networks (Maxout networks) on three benchmark datasets: MNIST, CIFAR-10…

Machine Learning · Computer Science 2015-09-24 Matthieu Courbariaux , Yoshua Bengio , Jean-Pierre David

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Fusheng Hao , Jun Cheng , Lei Wang , Xinchao Wang , Jianzhong Cao , Xiping Hu , Dapeng Tao

Deep learning models are trained and deployed in multiple domains. Increasing usage of deep learning models alarms the usage of memory consumed while computation by deep learning models. Existing approaches for reducing memory consumption…

Machine Learning · Computer Science 2021-10-25 Mahendran N

There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is…

Machine Learning · Computer Science 2019-10-08 Bernhard Bermeitinger , Tomas Hrycej , Siegfried Handschuh

Identifying critical nodes in networks is a classical decision-making task, and many methods struggle to strike a balance between adaptability and utility. Therefore, we propose an approach that empowers Evolutionary Algorithm (EA) with…

Social and Information Networks · Computer Science 2024-03-08 Jinzhu Mao , Dongyun Zou , Li Sheng , Siyi Liu , Chen Gao , Yue Wang , Yong Li

The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functions for a neural network output layer, like linear, sigmoid,…

Machine Learning · Computer Science 2025-11-10 Fernando Berzal

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained…

Machine Learning · Computer Science 2023-11-15 Vedant Nanda , Till Speicher , John P. Dickerson , Soheil Feizi , Krishna P. Gummadi , Adrian Weller

Gradient descent (GD) type optimization schemes are the standard instruments to train fully connected feedforward artificial neural networks (ANNs) with rectified linear unit (ReLU) activation and can be considered as temporal…

Optimization and Control · Mathematics 2022-02-24 Shokhrukh Ibragimov , Arnulf Jentzen , Timo Kröger , Adrian Riekert

We introduce techniques for exploring the functionality of a neural network and extracting simple, human-readable approximations to its performance. By performing gradient ascent on the input space of the network, we are able to produce…

High Energy Physics - Phenomenology · Physics 2018-04-26 Thomas Roxlo , Matthew Reece

An interesting approach to analyzing neural networks that has received renewed attention is to examine the equivalent kernel of the neural network. This is based on the fact that a fully connected feedforward network with one hidden layer,…

Machine Learning · Computer Science 2018-06-04 Russell Tsuchida , Farbod Roosta-Khorasani , Marcus Gallagher

Learning the latent network structure from large scale multivariate point process data is an important task in a wide range of scientific and business applications. For instance, we might wish to estimate the neuronal functional…

Methodology · Statistics 2021-01-21 Biao Cai , Jingfei Zhang , Yongtao Guan

Here we present a range-limited approach to centrality measures in both non-weighted and weighted directed complex networks. We introduce an efficient method that generates for every node and every edge its betweenness centrality based on…

Physics and Society · Physics 2011-11-24 Maria Ercsey-Ravasz , Ryan Lichtenwalter , Nitesh V. Chawla , Zoltan Toroczkai

In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…

Machine Learning · Computer Science 2020-06-15 Miltiadis Poursanidis , Jenny Benois-Pineau , Akka Zemmari , Boris Mansenca , Aymar de Rugy

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers.…

Machine Learning · Computer Science 2024-02-20 Chinmay Rane , Kanishka Tyagi , Michael Manry

We investigate deep morphological neural networks (DMNNs). We demonstrate that despite their inherent non-linearity, "linear" activations are essential for DMNNs. To preserve their inherent sparsity, we propose architectures that constraint…

Machine Learning · Computer Science 2025-12-24 Konstantinos Fotopoulos , Petros Maragos

Understanding the behavior of Artificial Neural Networks is one of the main topics in the field recently, as black-box approaches have become usual since the widespread of deep learning. Such high-dimensional models may manifest…

Machine Learning · Computer Science 2021-07-30 Leonardo F. S. Scabini , Odemir M. Bruno

We explore the potential for using a nonsmooth loss function based on the max-norm in the training of an artificial neural network. We hypothesise that this may lead to superior classification results in some special cases where the…

Machine Learning · Computer Science 2021-07-20 Vinesha Peiris , Nadezda Sukhorukova , Vera Roshchina

It is commonly recognized that the expressiveness of deep neural networks is contingent upon a range of factors, encompassing their depth, width, and other relevant considerations. Currently, the practical performance of the majority of…

Machine Learning · Computer Science 2023-11-08 Xuan Qi , Yi Wei

Contemporary deep learning based solution methods used to compute approximate equilibria of high-dimensional dynamic stochastic economic models are often faced with two pain points. The first problem is that the loss function typically…

General Economics · Economics 2023-03-28 Marlon Azinovic , Jan Žemlička

This paper leverages linear systems theory to propose a principled measure of complexity for network systems. We focus on a network of first-order scalar linear systems interconnected through a directed graph. By locally filtering out the…

Systems and Control · Electrical Eng. & Systems 2025-07-10 Giacomo Baggio , Marco Fabris