English
Related papers

Related papers: On-line learning and generalisation in coupled per…

200 papers

We investigate the generalization ability of a perceptron with non-monotonic transfer function of a reversed-wedge type in on-line mode. This network is identical to a parity machine, a multilayer network. We consider several learning…

Disordered Systems and Neural Networks · Physics 2009-10-30 Jun-ichi Inoue , Hidetoshi Nishimori , Yoshiyuki Kabashima

On-line learning of a rule given by an N-dimensional Ising perceptron, is considered for the case when the student is constrained to take values in a discrete state space of size $L^N$. For L=2 no on-line algorithm can achieve a finite…

Condensed Matter · Physics 2007-05-23 W. Kinzel , R. Urbanczik

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

The ability of deep learning models to generalize well across different scenarios depends primarily on the quality and quantity of annotated data. Labeling large amounts of data for all possible scenarios that a model may encounter would…

Machine Learning · Computer Science 2019-07-26 Qadeer Khan , Patrick Wenzel , Daniel Cremers , Laura Leal-Taixé

Imitation learning with a privileged teacher has proven effective for learning complex control behaviors from high-dimensional inputs, such as images. In this framework, a teacher is trained with privileged task information, while a student…

Robotics · Computer Science 2025-02-28 Nico Messikommer , Jiaxu Xing , Elie Aljalbout , Davide Scaramuzza

We investigate the influence of different kinds of structure on the learning behaviour of a perceptron performing a classification task defined by a teacher rule. The underlying pattern distribution is permitted to have spatial…

Disordered Systems and Neural Networks · Physics 2009-10-31 G. Dirscherl , B. Schottky , U. Krey

In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use…

Machine Learning · Computer Science 2024-07-18 Daniel Marczak , Sebastian Cygert , Tomasz Trzciński , Bartłomiej Twardowski

This paper proposes a latent space energy-based prior model for semi-supervised learning. The model stands on a generator network that maps a latent vector to the observed example. The energy term of the prior model couples the latent…

Machine Learning · Computer Science 2020-10-20 Bo Pang , Erik Nijkamp , Jiali Cui , Tian Han , Ying Nian Wu

We study theoretical guarantees for solving linear systems in-context using a linear transformer architecture. For in-domain generalization, we provide neural scaling laws that bound the generalization error in terms of the number of tasks…

Machine Learning · Computer Science 2025-05-27 Frank Cole , Yulong Lu , Wuzhe Xu , Tianhao Zhang

Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing. In this paper, we treat such pre-trained networks as teachers and explore how to learn a target…

Machine Learning · Computer Science 2019-05-29 Jingwen Ye , Xinchao Wang , Yixin Ji , Kairi Ou , Mingli Song

Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural…

Machine Learning · Statistics 2022-03-28 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

Conventional ensemble learning combines students in the space domain. On the other hand, in this paper we combine students in the time domain and call it time domain ensemble learning. In this paper, we analyze the generalization…

Statistical Mechanics · Physics 2009-11-11 Seiji Miyoshi , Tatsuya Uezu , Masato Okada

We propose an optimization method of mutual learning which converges into the identical state of optimum ensemble learning within the framework of on-line learning, and have analyzed its asymptotic property through the statistical mechanics…

Disordered Systems and Neural Networks · Physics 2015-05-13 Kazuyuki Hara , Takahiro Yamada

An unsupervised learning procedure based on maximizing the mutual information between the outputs of two networks receiving different but statistically dependent inputs is analyzed (Becker and Hinton, Nature, 355, 92, 161). For a generic…

Disordered Systems and Neural Networks · Physics 2009-11-10 Robert Urbanczik

Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have…

Machine Learning · Computer Science 2017-07-04 Yingce Xia , Tao Qin , Wei Chen , Jiang Bian , Nenghai Yu , Tie-Yan Liu

We introduce collaborative learning in which multiple classifier heads of the same network are simultaneously trained on the same training data to improve generalization and robustness to label noise with no extra inference cost. It…

Machine Learning · Statistics 2018-11-08 Guocong Song , Wei Chai

Over-parametrized deep neural networks trained by stochastic gradient descent are successful in performing many tasks of practical relevance. One aspect of over-parametrization is the possibility that the student network has a larger…

Disordered Systems and Neural Networks · Physics 2022-06-01 Frederieke Richert , Roman Worschech , Bernd Rosenow

Graphical models have been widely applied in solving distributed inference problems in sensor networks. In this paper, the problem of coordinating a network of sensors to train a unique ensemble estimator under communication constraints is…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-11-17 Haipeng Zheng , Sanjeev R. Kulkarni , H. Vincent Poor

Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks,…

Machine Learning · Computer Science 2025-01-09 Hui Wang , Cho Tung Yip , Bo Li

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well…

Computation and Language · Computer Science 2020-10-07 Xusen Yin , Ralph Weischedel , Jonathan May