English
Related papers

Related papers: UNREALIZABLE LEARNING IN FEEDFORWARD NEURAL NETWOR…

200 papers

We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground pattern. We develop a statistical mechanics framework to…

Disordered Systems and Neural Networks · Physics 2024-06-17 Alberto Fachechi , Elena Agliari , Miriam Aquaro , Anthony Coolen , Menno Mulder

A key problem in deep learning and computational neuroscience is relating the geometrical properties of neural representations to task performance. Here, we consider this problem for continuous decoding tasks where neural variability may…

Disordered Systems and Neural Networks · Physics 2025-07-01 Abdulkadir Canatar , SueYeon Chung

The existence of spurious correlations such as image backgrounds in the training environment can make empirical risk minimization (ERM) perform badly in the test environment. To address this problem, Kirichenko et al. (2022) empirically…

Machine Learning · Computer Science 2025-12-10 Haotian Ye , James Zou , Linjun Zhang

Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…

Computation and Language · Computer Science 2024-06-05 Henry Conklin , Kenny Smith

Many sensory pathways in the brain rely on sparsely active populations of neurons downstream from the input stimuli. The biological reason for the occurrence of expanded structure in the brain is unclear, but may be because expansion can…

Disordered Systems and Neural Networks · Physics 2021-02-24 Julia Steinberg , Madhu Advani , Haim Sompolinsky

Perceptual metrics are traditionally used to evaluate the quality of natural signals, such as images and audio. They are designed to mimic the perceptual behaviour of human observers and usually reflect structures found in natural signals.…

Sound · Computer Science 2023-12-07 Tashi Namgyal , Alexander Hepburn , Raul Santos-Rodriguez , Valero Laparra , Jesus Malo

Statistical physics approaches can be used to derive accurate predictions for the performance of inference methods learning from potentially noisy data, as quantified by the learning curve defined as the average error versus number of…

Machine Learning · Statistics 2012-11-07 Matthew J. Urry , Peter Sollich

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

A central question in computational neuroscience is how structure determines function in neural networks. The emerging high-quality large-scale connectomic datasets raise the question of what general functional principles can be gleaned…

Neurons and Cognition · Quantitative Biology 2022-10-25 Weishun Zhong , Ben Sorscher , Daniel D Lee , Haim Sompolinsky

With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems. However, despite their impressive performance on "known…

Machine Learning · Computer Science 2020-05-18 Mahum Naseer , Mishal Fatima Minhas , Faiq Khalid , Muhammad Abdullah Hanif , Osman Hasan , Muhammad Shafique

Learning unnormalized statistical models (e.g., energy-based models) is computationally challenging due to the complexity of handling the partition function. To eschew this complexity, noise-contrastive estimation~(NCE) has been proposed by…

Machine Learning · Computer Science 2023-06-14 Wei Jiang , Jiayu Qin , Lingyu Wu , Changyou Chen , Tianbao Yang , Lijun Zhang

In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input$\unicode{x2013}$output…

Machine Learning · Computer Science 2026-05-25 Vincent C. Brockers , Roman D. Ventzke , Valentin Neuhaus , Belén Hidalgo-Ogalde , Viola Priesemann

A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms. This is evidenced by their inability to generalize to data…

Machine Learning · Computer Science 2020-10-26 Yujun Yan , Kevin Swersky , Danai Koutra , Parthasarathy Ranganathan , Milad Hashemi

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Machine Learning · Computer Science 2024-08-12 Pietro Morerio , Ruggero Ragonesi , Vittorio Murino

In the framework of on-line learning, a learning machine might move around a teacher due to the differences in structures or output functions between the teacher and the learning machine or due to noises. The generalization performance of a…

Physics and Society · Physics 2009-11-11 Seiji Miyoshi , Masato Okada

Probabilistic representations, such as Bayesian and Markov networks, are fundamental to much of statistical machine learning. Thus, learning probabilistic representations directly from data is a deep challenge, the main computational…

Machine Learning · Computer Science 2020-06-16 Amelie Levray , Vaishak Belle

Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions…

Machine Learning · Computer Science 2026-05-11 Junjie Yu , Yue Wang , Zihan Deng , Yan Zhu , Wenxiao Ma , Quanying Liu

Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses. We study this phenomenon through the noise-to-signal ratio (NSR) of a policy-gradient estimator,…

Optimization and Control · Mathematics 2026-02-10 Haoyu Han , Heng Yang

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang