English
Related papers

Related papers: Empirical Evaluation of Rectified Activations in C…

200 papers

This paper introduces a significantly better class of activation functions than the almost universally used ReLU like and Sigmoidal class of activation functions. Two new activation functions referred to as the Cone and Parabolic-Cone that…

Artificial Intelligence · Computer Science 2024-05-08 Mathew Mithra Noel , Yug Oswal

ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of…

Machine Learning · Computer Science 2019-06-13 Jonathan Fiat , Eran Malach , Shai Shalev-Shwartz

This paper proposes a novel nonlinear activation mechanism typically for convolutional neural network (CNN), named as reborn mechanism. In sharp contrast to ReLU which cuts off the negative phase value, the reborn mechanism enjoys the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-08 Zhicheng Cai , Kaizhu Huang , Chenglei Peng

We investigate to what extent it is possible to solve linear inverse problems with $ReLu$ networks. Due to the scaling invariance arising from the linearity, an optimal reconstruction function $f$ for such a problem is positive homogeneous,…

Machine Learning · Computer Science 2023-08-08 Stefan Bamberger , Reinhard Heckel , Felix Krahmer

Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. This can be done using a combination of cryptographic and machine learning tools such as Convolutional Neural Networks (CNN). CNNs…

Computer Vision and Pattern Recognition · Computer Science 2021-01-29 Inbar Helbitz , Shai Avidan

We prove that two-layer (Leaky)ReLU networks initialized by e.g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are not universally consistent. Specifically, we describe a…

Machine Learning · Statistics 2022-06-10 David Holzmüller , Ingo Steinwart

Artificial neural networks usually consist of successive linear multiply-accumulate operations and nonlinear activation functions. However, most optical neural networks only achieve the linear operation in the optical domain, while the…

Optics · Physics 2023-11-03 Guanting Liu , Yiwei Shen , Ruiqian Li , Jingyi Yu , Xuming He , Cheng Wang

Artificial Neural Networks (ANN) have been employed for a range of modelling and prediction tasks using financial data. However, evidence on their predictive performance, especially for time-series data, has been mixed. Whereas some…

Risk Management · Quantitative Finance 2022-05-17 Philipp Ratz

We consider regression estimation with modified ReLU neural networks in which network weight matrices are first modified by a function $\alpha$ before being multiplied by input vectors. We give an example of continuous, piecewise linear…

Machine Learning · Statistics 2022-07-19 Aleksandr Beknazaryan , Hailin Sang

Convex relaxations are a key component of training and certifying provably safe neural networks. However, despite substantial progress, a wide and poorly understood accuracy gap to standard networks remains, raising the question of whether…

Machine Learning · Computer Science 2023-11-08 Maximilian Baader , Mark Niklas Müller , Yuhao Mao , Martin Vechev

Even in recent neural network architectures such as Transformers and Extended LSTM (xLSTM), and traditional ones like Convolutional Neural Networks, Activation Functions are an integral part of nearly all neural networks. They enable more…

Machine Learning · Computer Science 2024-10-01 Matias Roodschild , Jorge Gotay-Sardiñas , Victor A. Jimenez , Adrian Will

`Biologically inspired' activation functions, such as the logistic sigmoid, have been instrumental in the historical advancement of machine learning. However in the field of deep learning, they have been largely displaced by rectified…

Neural and Evolutionary Computing · Computer Science 2018-05-21 Gardave S Bhumbra

We present a novel methodology for repairing neural networks that use ReLU activation functions. Unlike existing methods that rely on modifying the weights of a neural network which can induce a global change in the function space, our…

Machine Learning · Computer Science 2022-07-25 Feisi Fu , Wenchao Li

Deep neural network with rectified linear units (ReLU) is getting more and more popular recently. However, the derivatives of the function represented by a ReLU network are not continuous, which limit the usage of ReLU network to situations…

Machine Learning · Computer Science 2020-12-03 Bo Li , Shanshan Tang , Haijun Yu

Large number of ReLU and MAC operations of Deep neural networks make them ill-suited for latency and compute-efficient private inference. In this paper, we present a model optimization method that allows a model to learn to be shallow. In…

Machine Learning · Computer Science 2023-04-27 Souvik Kundu , Yuke Zhang , Dake Chen , Peter A. Beerel

This paper investigates the ability of finite samples to identify two-layer irreducible shallow networks with various nonlinear activation functions, including rectified linear units (ReLU) and analytic functions such as the logistic…

Machine Learning · Computer Science 2025-03-18 Yu Xia , Zhiqiang Xu

In this paper, we propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost. We first construct a baseline network by modifying and…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Zechun Liu , Zhiqiang Shen , Marios Savvides , Kwang-Ting Cheng

The convolutional neural networks (CNN), including AlexNet, GoogleNet, VGGNet, etc. extract features for many computer vision problems which are very discriminative. The trained CNN model over one dataset performs reasonably well whereas on…

Computer Vision and Pattern Recognition · Computer Science 2022-01-25 Shiv Ram Dubey , Soumendu Chakraborty

Neural networks activated by the rectified linear unit (ReLU) play a central role in the recent development of deep learning. The topic of approximating functions from H\"older spaces by these networks is crucial for understanding the…

Machine Learning · Computer Science 2023-07-25 Tong Mao , Ding-Xuan Zhou

Current research suggests that the key factors in designing neural network architectures involve choosing number of filters for every convolution layer, number of hidden neurons for every fully connected layer, dropout and pruning. The…

Machine Learning · Computer Science 2020-09-17 Himanshu Pradeep Aswani , Amit Sethi