English
Related papers

Related papers: Regularizing RNNs by Stabilizing Activations

200 papers

Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' problems for training…

This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this context are commonly due…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Yang Zhong , Atsuto Maki

We present an efficient technique, which allows to train classification networks which are verifiably robust against norm-bounded adversarial attacks. This framework is built upon the work of Gowal et al., who applies the interval…

Machine Learning · Computer Science 2019-07-04 Paweł Morawiecki , Przemysław Spurek , Marek Śmieja , Jacek Tabor

Plasticity Loss is an increasingly important phenomenon that refers to the empirical observation that as a neural network is continually trained on a sequence of changing tasks, its ability to adapt to a new task diminishes over time. We…

Machine Learning · Computer Science 2025-09-30 Vivek F. Farias , Adam D. Jozefiak

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Machine Learning · Computer Science 2019-09-10 Dilin Wang , Chengyue Gong , Qiang Liu

Recent research demonstrate that prediction of time series by recurrent neural networks (RNNs) based on the noisy input generates a smooth anticipated trajectory. We examine the internal dynamics of RNNs and establish a set of conditions…

Machine Learning · Computer Science 2020-10-07 Boris Rubinstein

Exciting new work on the generalization bounds for neural networks (NN) given by Neyshabur et al. , Bartlett et al. closely depend on two parameter-depenedent quantities: the Lipschitz constant upper-bound and the stable rank (a softer…

Machine Learning · Statistics 2020-02-21 Amartya Sanyal , Philip H. S. Torr , Puneet K. Dokania

We propose a speech enhancement method using a causal deep neural network~(DNN) for real-time applications. DNN has been widely used for estimating a time-frequency~(T-F) mask which enhances a speech signal. One popular DNN structure for…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-17 Daiki Takeuchi , Kohei Yatabe , Yuma Koizumi , Yasuhiro Oikawa , Noboru Harada

Physics-guided neural networks (PGNN) is an effective tool that combines the benefits of data-driven modeling with the interpretability and generalization of underlying physical information. However, for a classical PGNN, the penalization…

Systems and Control · Electrical Eng. & Systems 2024-05-20 Yuhan Liu , Roland Tóth , Maarten Schoukens

We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can achieve encouraging accuracy on two types of syntactic patterns: context-free long distance agreement, and mildly context-sensitive cross serial…

Computation and Language · Computer Science 2022-08-12 Jean-Philippe Bernardy , Shalom Lappin

Aligning Large Language Models (LLMs) with human preferences typically relies on external supervision, which faces critical limitations: human annotations are scarce and subjective, reward models are vulnerable to reward hacking, and…

Computation and Language · Computer Science 2025-12-03 Yixuan Tang , Yi Yang

We propose aNETT (augmented NETwork Tikhonov) regularization as a novel data-driven reconstruction framework for solving inverse problems. An encoder-decoder type network defines a regularizer consisting of a penalty term that enforces…

Numerical Analysis · Mathematics 2021-02-09 Daniel Obmann , Linh Nguyen , Johannes Schwab , Markus Haltmeier

Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: \textbf{reward hacking} and \textbf{stable optimization}. Current solutions independently…

Machine Learning · Computer Science 2026-02-13 Li He , Qiang Qu , He Zhao , Stephen Wan , Dadong Wang , Lina Yao , Tongliang Liu

It was recently shown that the loss function used for training physics-informed neural networks (PINNs) exhibits local minima at solutions corresponding to fixed points of dynamical systems. In the forward setting, where the PINN is trained…

Machine Learning · Computer Science 2025-09-16 Milos Babic , Franz M. Rohrhofer , Bernhard C. Geiger

The use of deep learning has successfully solved several problems in the field of medical imaging. Deep learning has been applied to the CT denoising problem successfully. However, the use of deep learning requires large amounts of data to…

Image and Video Processing · Electrical Eng. & Systems 2022-04-04 Mayank Patwari , Ralf Gutjahr , Rainer Raupach , Andreas Maier

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Computation and Language · Computer Science 2026-01-09 Sharanya Dasgupta , Arkaprabha Basu , Sujoy Nath , Swagatam Das

An ongoing challenge in neural information processing is: how do neurons adjust their connectivity to improve task performance over time (i.e., actualize learning)? It is widely believed that there is a consistent, synaptic-level learning…

Neural and Evolutionary Computing · Computer Science 2021-06-01 Aman Bhargava , Mohammad R. Rezaei , Milad Lankarany

Graph Neural Networks (GNNs) have become widely-used models for semi-supervised learning. However, the robustness of GNNs in the presence of label noise remains a largely under-explored problem. In this paper, we consider an important yet…

Machine Learning · Computer Science 2023-02-28 Siyi Qian , Haochao Ying , Renjun Hu , Jingbo Zhou , Jintai Chen , Danny Z. Chen , Jian Wu

Recently, optimal time variable learning in deep neural networks (DNNs) was introduced in arXiv:2204.08528. In this manuscript we extend the concept by introducing a regularization term that directly relates to the time horizon in discrete…

Machine Learning · Computer Science 2023-12-07 Evelyn Herberg , Roland Herzog , Frederik Köhne

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Computation and Language · Computer Science 2025-05-27 Jinyan Su , Claire Cardie