English
Related papers

Related papers: Goldilocks Neural Networks

200 papers

Training Deep Convolutional Neural Networks (CNNs) is based on the notion of using multiple kernels and non-linearities in their subsequent activations to extract useful features. The kernels are used as general feature extractors without…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Alexandros Stergiou , Ronald Poppe , Remco C. Veltkamp

The widespread use of Multi-layer perceptrons (MLPs) often relies on a fixed activation function (e.g., ReLU, Sigmoid, Tanh) for all nodes within the hidden layers. While effective in many scenarios, this uniformity may limit the networks…

Machine Learning · Computer Science 2025-04-28 Hy Nguyen , Duy Khoa Pham , Srikanth Thudumu , Hung Du , Rajesh Vasa , Kon Mouzakis

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise…

Machine Learning · Computer Science 2023-10-03 Dmitry Chistikov , Matthias Englert , Ranko Lazic

Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language…

Machine Learning · Computer Science 2026-03-26 Emi Zeger , Mert Pilanci

Recently proposed neural network activation functions such as rectified linear, maxout, and local winner-take-all have allowed for faster and more effective training of deep neural architectures on large and complex datasets. The common…

Neural and Evolutionary Computing · Computer Science 2015-04-13 Rupesh Kumar Srivastava , Jonathan Masci , Faustino Gomez , Jürgen Schmidhuber

We present GLUScope, an open-source tool for analyzing neurons in Transformer-based language models, intended for interpretability researchers. We focus on more recent models than previous tools do; specifically we consider gated activation…

Computation and Language · Computer Science 2026-03-02 Sebastian Gerstner , Hinrich Schütze

A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised deep learning,…

There currently exist two extreme viewpoints for neural network feature learning -- (i) Neural networks simply implement a kernel method (a la NTK) and hence no features are learned (ii) Neural networks can represent (and hence learn)…

Machine Learning · Computer Science 2024-04-09 Mahesh Lorik Yadav , Harish Guruprasad Ramaswamy , Chandrashekar Lakshminarayanan

Activation functions play a pivotal role in the function learning using neural networks. The non-linearity in the learned function is achieved by repeated use of the activation function. Over the years, numerous activation functions have…

Machine Learning · Computer Science 2020-10-13 Koushik Biswas , Sandeep Kumar , Shilpak Banerjee , Ashish Kumar Pandey

Today, it is more important than ever before for users to have trust in the models they use. As Machine Learning models fall under increased regulatory scrutiny and begin to see more applications in high-stakes situations, it becomes…

Machine Learning · Computer Science 2020-12-03 William Knauth

The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images. However, in practice, it is highly desirable to establish a progressive structure for…

Computer Vision and Pattern Recognition · Computer Science 2018-04-27 Zhi Zhang , Guanghan Ning , Yigang Cen , Yang Li , Zhiqun Zhao , Hao Sun , Zhihai He

A wide variety of activation functions have been proposed for neural networks. The Rectified Linear Unit (ReLU) is especially popular today. There are many practical reasons that motivate the use of the ReLU. This paper provides new…

Machine Learning · Statistics 2020-10-19 Rahul Parhi , Robert D. Nowak

Deep networks are often considered to be more expressive than shallow ones in terms of approximation. Indeed, certain functions can be approximated by deep networks provably more efficiently than by shallow ones, however, no tractable…

Machine Learning · Statistics 2021-08-27 Alberto Bietti , Francis Bach

This paper explores the expressive power of deep neural networks for a diverse range of activation functions. An activation function set $\mathscr{A}$ is defined to encompass the majority of commonly used activation functions, such as…

Machine Learning · Computer Science 2024-02-28 Shijun Zhang , Jianfeng Lu , Hongkai Zhao

We introduce collaborative learning in which multiple classifier heads of the same network are simultaneously trained on the same training data to improve generalization and robustness to label noise with no extra inference cost. It…

Machine Learning · Statistics 2018-11-08 Guocong Song , Wei Chai

Neural networks with at least two hidden layers are called deep networks. Recent developments in AI and computer programming in general has led to development of tools such as Tensorflow, Keras, NumPy etc. making it easier to model and draw…

Signal Processing · Electrical Eng. & Systems 2021-03-30 Ruthvik Vaila , Denver Lloyd , Kevin Tetz

Spintronic technology is emerging as a direction for the hardware implementation of neurons and synapses of neuromorphic architectures. In particular, a single spintronic device can be used to implement the nonlinear activation function of…

We focus on the robustness of neural networks for classification. To permit a fair comparison between methods to achieve robustness, we first introduce a standard based on the mensuration of a classifier's degradation. Then, we propose…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Sadaf Gulshad , Arnold Smeulders

We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is in the center of interest. We compute typical learning…

Machine Learning · Computer Science 2020-11-13 Elisa Oostwal , Michiel Straat , Michael Biehl

In this paper, we propose novel quaternion activation functions where we modify either the quaternion magnitude or the phase, as an alternative to the commonly used split activation functions. We define criteria that are relevant for…

Machine Learning · Computer Science 2024-06-25 Johannes Pöppelbaum , Andreas Schwung
‹ Prev 1 8 9 10 Next ›