English
Related papers

Related papers: Farkas layers: don't shift the data, fix the geome…

200 papers

ReLU neural networks define piecewise linear functions of their inputs. However, initializing and training a neural network is very different from fitting a linear spline. In this paper, we expand empirically upon previous theoretical work…

Machine Learning · Statistics 2016-11-30 Kevin K. Chen , Anthony Gamst , Alden Walker

Deep neural networks are usually initialized with random weights, with adequately selected initial variance to ensure stable signal propagation during training. However, selecting the appropriate variance becomes challenging especially as…

Machine Learning · Computer Science 2022-11-07 Jiawei Zhao , Florian Schäfer , Anima Anandkumar

In this work, we suggest Kernel Filtering Linear Overparameterization (KFLO), where a linear cascade of filtering layers is used during training to improve network performance in test time. We implement this cascade in a kernel filtering…

Machine Learning · Computer Science 2022-07-13 Amit Henig , Raja Giryes

The complexity of black-box algorithms can lead to various challenges, including the introduction of biases. These biases present immediate risks in the algorithms' application. It was, for instance, shown that neural networks can deduce…

Machine Learning · Computer Science 2024-06-04 David Rügamer , Chris Kolb , Tobias Weber , Lucas Kook , Thomas Nagler

In recent years significant progress has been made in successfully training recurrent neural networks (RNNs) on sequence learning problems involving long range temporal dependencies. The progress has been made on three fronts: (a)…

Neural and Evolutionary Computing · Computer Science 2016-06-24 Sachin S. Talathi , Aniket Vartak

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

Optimization and Control · Mathematics 2019-07-26 S. Günther , L. Ruthotto , J. B. Schroder , E. C. Cyr , N. R. Gauger

We consider neural networks with rational activation functions. The choice of the nonlinear activation function in deep learning architectures is crucial and heavily impacts the performance of a neural network. We establish optimal bounds…

Neural and Evolutionary Computing · Computer Science 2020-10-01 Nicolas Boullé , Yuji Nakatsukasa , Alex Townsend

We present a method for training a deep neural network containing sinusoidal activation functions to fit to time-series data. Weights are initialized using a fast Fourier transform, then trained with regularization to improve…

Neural and Evolutionary Computing · Computer Science 2014-05-12 Michael S. Gashler , Stephen C. Ashmore

We propose a simple extension to the ReLU-family of activation functions that allows them to shift the mean activation across a layer towards zero. Combined with proper weight initialization, this alleviates the need for normalization…

Machine Learning · Statistics 2018-03-16 Lars Eidnes , Arild Nøkland

The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions, each corresponding to a specific activation pattern of the included ReLU-like activations. We demonstrate that this partition…

Machine Learning · Computer Science 2021-01-15 Fengxiang He , Shiye Lei , Jianmin Ji , Dacheng Tao

We study the improper learning of multi-layer neural networks. Suppose that the neural network to be learned has $k$ hidden layers and that the $\ell_1$-norm of the incoming weights of any neuron is bounded by $L$. We present a kernel-based…

Machine Learning · Computer Science 2015-10-14 Yuchen Zhang , Jason D. Lee , Michael I. Jordan

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy

This paper presents a new mathematical framework to analyze the loss functions of deep neural networks with ReLU functions. Furthermore, as as application of this theory, we prove that the loss functions can reconstruct the inputs of the…

Machine Learning · Statistics 2018-05-21 Akiyoshi Sannai

Normalization methods play an important role in enhancing the performance of deep learning while their theoretical understandings have been limited. To theoretically elucidate the effectiveness of normalization, we quantify the geometry of…

Machine Learning · Statistics 2019-10-29 Ryo Karakida , Shotaro Akaho , Shun-ichi Amari

In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of…

Machine Learning · Computer Science 2018-10-16 Otkrist Gupta , Ramesh Raskar

We propose layer saturation - a simple, online-computable method for analyzing the information processing in neural networks. First, we show that a layer's output can be restricted to the eigenspace of its variance matrix without…

Machine Learning · Computer Science 2021-11-23 Mats L. Richter , Justin Shenk , Wolf Byttner , Anders Arpteg , Mikael Huss

Each year, deep learning demonstrates new and improved empirical results with deeper and wider neural networks. Meanwhile, with existing theoretical frameworks, it is difficult to analyze networks deeper than two layers without resorting to…

Machine Learning · Computer Science 2023-03-28 Hong Jun Jeon , Yifan Zhu , Benjamin Van Roy

We introduce a new class of non-linear models for functional data based on neural networks. Deep learning has been very successful in non-linear modeling, but there has been little work done in the functional data setting. We propose two…

Machine Learning · Computer Science 2023-05-11 Aniruddha Rajendra Rao , Matthew Reimherr

In this work, we propose to train a deep neural network by distributed optimization over a graph. Two nonlinear functions are considered: the rectified linear unit (ReLU) and a linear unit with both lower and upper cutoffs (DCutLU). The…

Machine Learning · Computer Science 2017-06-20 Guoqiang Zhang , W. Bastiaan Kleijn

Despite their increasing popularity and success in a variety of supervised learning problems, deep neural networks are extremely hard to interpret and debug: Given and already trained Deep Neural Net, and a set of test inputs, how can we…

Machine Learning · Computer Science 2018-06-07 Uday Singh Saini , Evangelos E. Papalexakis