English
Related papers

Related papers: Explicit Computation of Input Weights in Extreme L…

200 papers

This paper presents a novel method for autonomously enhancing deep neural network training. My approach employs an Evaluation Neural Network (ENN) trained via deep reinforcement learning to predict the performance of the target network. The…

Machine Learning · Computer Science 2024-06-18 Ryohei Ino

A learning algorithm for multilayer perceptrons is presented which is based on finding the principal components of a correlation matrix computed from the example inputs and their target outputs. For large networks our procedure needs far…

Disordered Systems and Neural Networks · Physics 2007-05-23 C. Bunzmann , M. Biehl , R. Urbanczik

In recent years neural networks have achieved state-of-the-art accuracy for various tasks but the the interpretation of the generated outputs still remains difficult. In this work we attempt to provide a method to understand the learnt…

Machine Learning · Computer Science 2022-05-25 Siddhartha

How is knowledge stored in an LLM's weights? We study this via layer pruning: if removing a certain layer does not affect model performance in common question-answering benchmarks, then the weights in that layer are not necessary for…

Computation and Language · Computer Science 2025-03-04 Andrey Gromov , Kushal Tirumala , Hassan Shapourian , Paolo Glorioso , Daniel A. Roberts

In this work, we firstly apply the Train-Tensor (TT) networks to construct a compact representation of the classical Multilayer Perceptron, representing a reduction of up to 95% of the coefficients. A comparative analysis between tensor…

Machine Learning · Computer Science 2021-03-31 M. Nazareth da Costa , R. Attux , A. Cichocki , J. M. T. Romano

In this paper, a Neural network is derived from first principles, assuming only that each layer begins with a linear dimension-reducing transformation. The approach appeals to the principle of Maximum Entropy (MaxEnt) to find the posterior…

Machine Learning · Statistics 2020-02-19 Paul M Baggenstoss

Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters. Tuning these weights with random search or Bayesian…

Machine Learning · Computer Science 2026-05-11 Ivan Karpukhin , Andrey Savchenko

Hypernetworks are meta neural networks that generate weights for a main neural network in an end-to-end differentiable manner. Despite extensive applications ranging from multi-task learning to Bayesian deep learning, the problem of…

Machine Learning · Computer Science 2023-12-15 Oscar Chang , Lampros Flokas , Hod Lipson

Learning energy-based model (EBM) requires MCMC sampling of the learned model as an inner loop of the learning algorithm. However, MCMC sampling of EBMs in high-dimensional data space is generally not mixing, because the energy function,…

Machine Learning · Statistics 2022-03-17 Erik Nijkamp , Ruiqi Gao , Pavel Sountsov , Srinivas Vasudevan , Bo Pang , Song-Chun Zhu , Ying Nian Wu

In this work we propose a HyperTransformer, a Transformer-based model for supervised and semi-supervised few-shot learning that generates weights of a convolutional neural network (CNN) directly from support samples. Since the dependence of…

Machine Learning · Computer Science 2022-07-15 Andrey Zhmoginov , Mark Sandler , Max Vladymyrov

This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized,…

Probability · Mathematics 2021-02-17 Lukas Gonon , Lyudmila Grigoryeva , Juan-Pablo Ortega

Weight initialization governs signal propagation and gradient flow at the start of training. This paper offers a theory-grounded and empirically validated study across two regimes: compact ReLU multilayer perceptrons and GPT-2-style…

Machine Learning · Computer Science 2025-10-13 Yankun Han

It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time. With this ability, new class labels could be assigned to these inputs by a…

Machine Learning · Computer Science 2017-05-23 Ethan M. Rudd , Lalit P. Jain , Walter J. Scheirer , Terrance E. Boult

Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient…

Computation and Language · Computer Science 2025-10-14 Sunbowen Lee , Qingyu Yin , Chak Tou Leong , Jialiang Zhang , Yicheng Gong , Shiwen Ni , Min Yang , Xiaoyu Shen

Within the framework of on-line learning, we study the generalization error of an ensemble learning machine learning from a linear teacher perceptron. The generalization error achieved by an ensemble of linear perceptrons having homogeneous…

Disordered Systems and Neural Networks · Physics 2009-11-10 Kazuyuki Hara , Masato Okada

Deep learning based techniques achieve state-of-the-art results in a wide range of image reconstruction tasks like compressed sensing. These methods almost always have hyperparameters, such as the weight coefficients that balance the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Alan Q. Wang , Adrian V. Dalca , Mert R. Sabuncu

Informed by the basic geometry underlying feed forward neural networks, we initialize the weights of the first layer of a neural network using the linear discriminants which best distinguish individual classes. Networks initialized in this…

Machine Learning · Computer Science 2020-08-19 Marissa Masden , Dev Sinha

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Machine Learning · Computer Science 2026-04-22 Ziqian Zhong , Aditi Raghunathan

In this paper, we propose a novel approach based on cost-sensitive ensemble weighted extreme learning machine; we call this approach AE1-WELM. We apply this approach to text classification. AE1-WELM is an algorithm including balanced and…

Information Retrieval · Computer Science 2018-05-18 Ming Li , Peilun Xiao , Ju Zhang

ELMo embeddings (Peters et. al, 2018) had a huge impact on the NLP community and may recent publications use these embeddings to boost the performance for downstream NLP tasks. However, integration of ELMo embeddings in existent NLP…

Computation and Language · Computer Science 2019-04-08 Nils Reimers , Iryna Gurevych
‹ Prev 1 4 5 6 7 8 10 Next ›