English
Related papers

Related papers: The Forward-Forward Algorithm: Characterizing Trai…

200 papers

This article introduces a novel approach to learning monotone neural networks through a newly defined penalization loss. The proposed method is particularly effective in solving classes of variational problems, specifically monotone…

Optimization and Control · Mathematics 2025-03-07 Younes Belkouchi , Jean-Christophe Pesquet , Audrey Repetti , Hugues Talbot

The number of parameters in state of the art neural networks has drastically increased in recent years. This surge of interest in large scale neural networks has motivated the development of new distributed training strategies enabling such…

Machine Learning · Computer Science 2022-07-11 Aidan N. Gomez , Oscar Key , Kuba Perlin , Stephen Gou , Nick Frosst , Jeff Dean , Yarin Gal

The purpose of this paper is to propose a new multi-layer feedforward quaternion neural network model architecture, Reverse Quaternion Neural Network which utilizes the non-commutative nature of quaternion products, and to clarify its…

Neural and Evolutionary Computing · Computer Science 2025-08-14 Shogo Yamauchi , Tohru Nitta , Takaaki Ohnishi

Advanced feedforward control methods enable mechatronic systems to perform varying motion tasks with extreme accuracy and throughput. The aim of this paper is to develop a data-driven feedforward controller that addresses input…

Systems and Control · Electrical Eng. & Systems 2023-11-30 Jilles van Hulst , Maurice Poot , Dragan Kostić , Kai Wa Yan , Jim Portegies , Tom Oomen

Currently, the most successful learning models in computer vision are based on learning successive representations followed by a decision layer. This is usually actualized through feedforward multilayer neural networks, e.g. ConvNets, where…

Computer Vision and Pattern Recognition · Computer Science 2017-08-22 Amir R. Zamir , Te-Lin Wu , Lin Sun , William Shen , Jitendra Malik , Silvio Savarese

Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with…

Machine Learning · Computer Science 2025-02-24 Yizhou Xu , Liu Ziyin

We introduce a new method for learning Bayesian neural networks, treating them as a stack of multivariate Bayesian linear regression models. The main idea is to infer the layerwise posterior exactly if we know the target outputs of each…

Machine Learning · Computer Science 2024-11-20 Richard Kurle , Alexej Klushyn , Ralf Herbrich

We introduce a new online approach for constructing proposal distributions in particle filters using a forward scheme. Our method progressively incorporates future observations to refine proposals. This is in contrast to backward-scheme…

Computation · Statistics 2026-01-23 Sylvain Procope-Mamert , Nicolas Chopin , Maud Delattre , Guillaume Kon Kam King

Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized…

Machine Learning · Statistics 2026-05-19 Grigory Bartosh , Teodora Pandeva , Sushrut Karmalkar , Javier Zazo

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

Transfer learning is a powerful tool enabling model training with limited amounts of data. This technique is particularly useful in real-world problems where data availability is often a serious limitation. The simplest transfer learning…

Machine Learning · Computer Science 2023-03-03 Federica Gerace , Diego Doimo , Stefano Sarao Mannelli , Luca Saglietti , Alessandro Laio

This paper addresses the limitations in Optical Neural Networks (ONNs) related to training efficiency, nonlinear function implementation, and large input data processing. We introduce Two-Pass Forward Propagation, a novel training method…

Machine Learning · Computer Science 2024-08-19 Amirreza Ahmadnejad , Somayyeh Koohi

It is widely believed that deep neural networks contain layer specialization, wherein neural networks extract hierarchical features representing edges and patterns in shallow layers and complete objects in deeper layers. Unlike common…

Machine Learning · Computer Science 2022-03-04 Avi Schwarzschild , Arjun Gupta , Amin Ghiasi , Micah Goldblum , Tom Goldstein

Deep learning (DL) has achieved great success in many applications, but it has been less well analyzed from the theoretical perspective. The unexplainable success of black-box DL models has raised questions among scientists and promoted the…

Robotics · Computer Science 2023-08-25 Huu-Thiet Nguyen , Chien Chern Cheah , Kar-Ann Toh

Catastrophic forgetting remains a central challenge in continual learning (CL) with pre-trained models. While existing approaches typically freeze the backbone and fine-tune a small number of parameters to mitigate forgetting, they still…

Machine Learning · Computer Science 2025-09-03 Jiao Chen , Jiayi He , Fangfang Chen , Zuohong Lv , Jianhua Tang

This work identifies a simple pre-training mechanism that leads to representations exhibiting better continual and transfer learning. This mechanism -- the repeated resetting of weights in the last layer, which we nickname "zapping" -- was…

Machine Learning · Computer Science 2024-10-22 Lapo Frati , Neil Traft , Jeff Clune , Nick Cheney

We propose a supervised learning algorithm for machine learning applications. Contrary to the model developing in the classical methods, which treat training, validation, and test as separate steps, in the presented approach, there is a…

Machine Learning · Computer Science 2019-09-24 Soheil Mehrabkhani

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

Linear transformation of the inputs alters the training performance of feed-forward networks that are otherwise equivalent. However, most linear transforms are viewed as a pre-processing operation separate from the actual training. Starting…

Machine Learning · Computer Science 2023-04-03 Chinmay Rane , Kanishka Tyagi , Sanjeev Malalur , Yash Shinge , Michael Manry

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models…