中文
相关论文

相关论文: Riemannian metrics for neural networks I: feedforw…

200 篇论文

For many types of machine learning algorithms, one can compute the statistically `optimal' way to select training data. In this paper, we review how optimal data selection techniques have been used with feedforward neural networks. We then…

人工智能 · 计算机科学 2014-11-17 D. A. Cohn , Z. Ghahramani , M. I. Jordan

Hierarchical neural networks are exponentially more efficient than their corresponding "shallow" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. Our main idea is to…

机器学习 · 计算机科学 2018-07-19 Bálint Daróczy , Rita Aleksziev , András Benczúr

A deep neural network is a hierarchical nonlinear model transforming input signals to output signals. Its input-output relation is considered to be stochastic, being described for a given input by a parameterized conditional probability…

机器学习 · 计算机科学 2018-08-23 Shun-ichi Amari , Ryo Karakida , Masafumi Oizumi

We propose a hierarchical training algorithm for standard feed-forward neural networks that adaptively extends the network architecture as soon as the optimization reaches a stationary point. By solving small (low-dimensional) optimization…

数值分析 · 数学 2024-10-31 Michael Feischl , Alexander Rieder , Fabian Zehetgruber

The process of training feedforward neural networks (FFNNs) can benefit from an automated process where the best heuristic to train the network is sought out automatically by means of a high-level probabilistic-based heuristic. This…

机器学习 · 计算机科学 2024-09-10 Arné Schreuder , Anna Bosman , Andries Engelbrecht , Christopher Cleghorn

The single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature. The advantage of these networks is their simplified training, which reduces to solving a ridge-regression problem. A…

机器学习 · 计算机科学 2025-02-25 M. Andrecut

Recurrent neural networks are powerful models for sequential data, able to represent complex dependencies in the sequence that simpler models such as hidden Markov models cannot handle. Yet they are notoriously hard to train. Here we…

神经与进化计算 · 计算机科学 2015-02-04 Yann Ollivier

We propose automatic optimisation methods considering the geometry of matrix manifold for the normalised parameters of neural networks. Layerwise weight normalisation with respect to Frobenius norm is utilised to bound the Lipschitz…

机器学习 · 计算机科学 2023-12-19 Namhoon Cho , Hyo-Sang Shin

We present practical Levenberg-Marquardt variants of Gauss-Newton and natural gradient methods for solving non-convex optimization problems that arise in training deep neural networks involving enormous numbers of variables and huge data…

机器学习 · 计算机科学 2019-06-07 Yi Ren , Donald Goldfarb

The aim of this project is to develop a code to discover the optimal sigma value that maximum the F1 score and the optimal sigma value that maximizes the accuracy and to find out if they are the same. Four algorithms which can be used to…

系统与控制 · 电气工程与系统科学 2019-11-19 Alison Jenkins , Vinika Gupta , Mary Lenoir

We present a simple linear regression based approach for learning the weights and biases of a neural network, as an alternative to standard gradient based backpropagation. The present work is exploratory in nature, and we restrict the…

机器学习 · 计算机科学 2023-07-17 Harshad Khadilkar

Feedforward neural networks with random hidden nodes suffer from a problem with the generation of random weights and biases as these are difficult to set optimally to obtain a good projection space. Typically, random parameters are drawn…

机器学习 · 计算机科学 2019-09-18 Grzegorz Dudek

A sequential training method for large-scale feedforward neural networks is presented. Each layer of the neural network is decoupled and trained separately. After the training is completed for each layer, they are combined together. The…

机器学习 · 计算机科学 2019-05-21 Jongrae Kim

We consider machine learning tasks with low-rank functional tree tensor networks (TTN) as the learning model. While in the case of least-squares regression, low-rank functional TTNs can be efficiently optimized using alternating…

最优化与控制 · 数学 2026-04-13 Nikolas Klug , Michael Ulbrich , André Uschmajew , Marius Willner

The paper addresses the problem of learning a regression model parameterized by a fixed-rank positive semidefinite matrix. The focus is on the nonlinear nature of the search space and on scalability to high-dimensional problems. The…

机器学习 · 计算机科学 2011-02-01 Gilles Meyer , Silvere Bonnabel , Rodolphe Sepulchre

After the tremendous development of neural networks trained by backpropagation, it is a good time to develop other algorithms for training neural networks to gain more insights into networks. In this paper, we propose a new algorithm for…

机器学习 · 计算机科学 2020-07-01 Benyamin Ghojogh , Fakhri Karray , Mark Crowley

Understanding how systems built out of modular components can be jointly optimized is an important problem in biology, engineering, and machine learning. The backpropagation algorithm is one such solution and has been instrumental in the…

机器学习 · 计算机科学 2026-03-05 Christian Pehle , Jean-Jacques Slotine

Physics-informed neural networks approach the approximation of differential equations by directly incorporating their structure and given conditions in a loss function. This enables conditions like, e.g., invariants to be easily added…

机器学习 · 计算机科学 2025-08-20 Santosh Humagain , Toni Schneidereit

We provide novel guaranteed approaches for training feedforward neural networks with sparse connectivity. We leverage on the techniques developed previously for learning linear networks and show that they can also be effectively adopted to…

机器学习 · 计算机科学 2015-04-29 Hanie Sedghi , Anima Anandkumar

We develop an approach to efficiently grow neural networks, within which parameterization and optimization strategies are designed by considering their effects on the training dynamics. Unlike existing growing methods, which follow simple…

机器学习 · 计算机科学 2023-06-23 Xin Yuan , Pedro Savarese , Michael Maire
‹ 上一页 1 2 3 10 下一页 ›