English
Related papers

Related papers: Dissecting a Small Artificial Neural Network

200 papers

Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We…

Machine Learning · Computer Science 2013-03-12 Tommi Vatanen , Tapani Raiko , Harri Valpola , Yann LeCun

Dynamical loss functions are derived from standard loss functions used in supervised classification tasks, but are modified so that the contribution from each class periodically increases and decreases. These oscillations globally alter the…

Machine Learning · Computer Science 2025-11-06 Eduardo Lavin Pallero , Miguel Ruiz-Garcia

The contemporary scientific landscape is characterized by a "curse of dimensionality," where our capacity to collect high-dimensional network data frequently outstrips our ability to computationally simulate or intuitively comprehend the…

General Physics · Physics 2026-02-03 Zebiao Li , XueYing Wu , Chengyi Tu

Gradient descent has been a central training principle for artificial neural networks from the early beginnings to today's deep learning networks. The most common implementation is the backpropagation algorithm for training feed-forward…

Machine Learning · Computer Science 2020-06-09 Stefan Jaeger

While artificial neural networks are known as universal approximators for continuous functions, many modern approaches rely on overparameterized architectures with high computational cost. In this work, we introduce the Barycentric Neural…

Machine Learning · Computer Science 2025-10-10 Victor Toscano-Duran , Rocio Gonzalez-Diaz , Miguel A. Gutiérrez-Naranjo

We propose a novel loss function that dynamically rescales the cross entropy based on prediction difficulty regarding a sample. Deep neural network architectures in image classification tasks struggle to disambiguate visually similar…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Serim Ryou , Seong-Gyun Jeong , Pietro Perona

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

Neural and Evolutionary Computing · Computer Science 2024-11-06 Mathew Mithra Noel , Arindam Banerjee , Yug Oswal , Geraldine Bessie Amali D , Venkataraman Muthiah-Nakarajan

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially…

Machine Learning · Computer Science 2018-06-05 Simon S. Du , Surbhi Goel

In artificial neural networks, learning from data is a computationally demanding task in which a large number of connection weights are iteratively tuned through stochastic-gradient-based heuristic processes over a cost-function. It is not…

Neural network based machine learning is emerging as a powerful tool for obtaining phase diagrams when traditional regression schemes using local equilibrium order parameters are not available, as in many-body localized or topological…

Disordered Systems and Neural Networks · Physics 2018-06-27 Jordan Venderley , Vedika Khemani , Eun-Ah Kim

When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) the class means and the last-layer classifiers all collapse to…

Machine Learning · Computer Science 2022-03-15 Jinxin Zhou , Xiao Li , Tianyu Ding , Chong You , Qing Qu , Zhihui Zhu

Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is…

Machine Learning · Computer Science 2017-12-25 Pierre Baldi , Peter Sadowski , Zhiqin Lu

A computer model of the feed-forward neural network with the hidden layer is developed to reconstruct physical field investigated by the fiber-optic measuring system. The Gaussian distributions of some physical quantity are selected as…

Disordered Systems and Neural Networks · Physics 2007-05-23 A. V. Panov

With increasing scale in model and dataset size, the training of deep neural networks becomes a massive computational burden. One approach to speed up the training process is Selective Backprop. For this approach, we perform a forward pass…

Machine Learning · Computer Science 2023-12-11 Lukas Balles , Cedric Archambeau , Giovanni Zappella

We study the implicit bias of gradient flow (i.e., gradient descent with infinitesimal step size) on linear neural network training. We propose a tensor formulation of neural networks that includes fully-connected, diagonal, and…

Machine Learning · Computer Science 2021-09-13 Chulhee Yun , Shankar Krishnan , Hossein Mobahi

From the proliferative mechanisms generating neurons from progenitor cells to neuron migration and synaptic connection formation, several vicissitudes culminate in the mature brain. Both component loss and gain remain ubiquitous during…

Neurons and Cognition · Quantitative Biology 2024-08-06 Rodrigo Siqueira Kazu , Kleber Neves , Bruno Mota

Neural Collapse is a phenomenon where the last-layer representations of a well-trained neural network converge to a highly structured geometry. In this paper, we focus on its first (and most basic) property, known as NC1: the within-class…

Machine Learning · Computer Science 2025-02-05 Diyuan Wu , Marco Mondelli

Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical…

Machine Learning · Statistics 2017-05-25 Anna C. Gilbert , Yi Zhang , Kibok Lee , Yuting Zhang , Honglak Lee

The landscape of low-energy effective field theories stemming from string theory is too vast for a systematic exploration. However, the meadows of the string landscape may be fertile ground for the application of machine learning…

High Energy Physics - Theory · Physics 2024-03-07 Stefano Lanza

Artificial neural networks (ANNs), while exceptionally useful for classification, are vulnerable to misdirection. Small amounts of noise can significantly affect their ability to correctly complete a task. Instead of generalizing concepts,…

Neural and Evolutionary Computing · Computer Science 2018-04-06 Arend Hintze , Douglas Kirkpatrick , Christoph Adami
‹ Prev 1 3 4 5 6 7 10 Next ›