English
Related papers

Related papers: Dynamical Isometry for Residual Networks

200 papers

The Residual Networks of Residual Networks (RoR) exhibits excellent performance in the image classification task, but sharply increasing the number of feature map channels makes the characteristic information transmission incoherent, which…

Computer Vision and Pattern Recognition · Computer Science 2017-10-03 Ke Zhang , Liru Guo , Ce Gao , Zhenbing Zhao

We propose a simultaneous learning and pruning algorithm capable of identifying and eliminating irrelevant structures in a neural network during the early stages of training. Thus, the computational cost of subsequent training iterations,…

Machine Learning · Computer Science 2023-01-16 Valentin Frank Ingmar Guenter , Athanasios Sideris

The practice of deep learning has shown that neural networks generalize remarkably well even with an extreme number of learned parameters. This appears to contradict traditional statistical wisdom, in which a trade-off between model…

Machine Learning · Computer Science 2023-02-21 Yifei Wang , Yixuan Hua , Emmanuel Candés , Mert Pilanci

Ensembling fine-tuned models initialized from powerful pre-trained weights is a common strategy to improve robustness under distribution shifts, but it comes with substantial computational costs due to the need to train and store multiple…

Machine Learning · Computer Science 2025-10-13 Masih Aminbeidokhti , Heitor Rapela Medeiros , Srikanth Muralidharan , Eric Granger , Marco Pedersoli

We present a scheme for sequential decision making with a risk-sensitive objective and constraints in a dynamic environment. A neural network is trained as an approximator of the mapping from parameter space to space of risk and policy with…

Artificial Intelligence · Computer Science 2019-07-10 Shuai Ma , Jia Yuan Yu , Ahmet Satir

Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-24 Saeed Anwar , Nick Barnes

Despite the striking successes of deep neural networks trained with gradient-based optimization, these methods differ fundamentally from their biological counterparts. This gap raises key questions about how nature achieves robust,…

Machine Learning · Computer Science 2025-10-15 Mattia Scardecchia

We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw.…

We present a new approach for input optimization of ReLU networks that explicitly takes into account the effect of changes in activation patterns. We analyze local optimization steps in both the input space and the space of activation…

Machine Learning · Computer Science 2024-06-04 Hongzhan Yu , Sicun Gao

Deep learning, in the form of artificial neural networks, has achieved remarkable practical success in recent years, for a variety of difficult machine learning applications. However, a theoretical explanation for this remains a major open…

Machine Learning · Computer Science 2016-06-15 Itay Safran , Ohad Shamir

Standard practice in training neural networks involves initializing the weights in an independent fashion. The results of recent work suggest that feature "diversity" at initialization plays an important role in training the network.…

Machine Learning · Computer Science 2020-07-06 Yaniv Blumenfeld , Dar Gilboa , Daniel Soudry

Hyperparameter optimization is crucial for obtaining peak performance of machine learning models. The standard protocol evaluates various hyperparameter configurations using a resampling estimate of the generalization error to guide…

Machine Learning · Statistics 2024-11-11 Thomas Nagler , Lennart Schneider , Bernd Bischl , Matthias Feurer

Residual networks (Resnets) have become a prominent architecture in deep learning. However, a comprehensive understanding of Resnets is still a topic of ongoing research. A recent view argues that Resnets perform iterative refinement of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-09 Stanisław Jastrzębski , Devansh Arpit , Nicolas Ballas , Vikas Verma , Tong Che , Yoshua Bengio

This paper proposes ReBNet, an end-to-end framework for training reconfigurable binary neural networks on software and developing efficient accelerators for execution on FPGA. Binary neural networks offer an intriguing opportunity for…

Machine Learning · Computer Science 2018-03-29 Mohammad Ghasemzadeh , Mohammad Samragh , Farinaz Koushanfar

The expressivity of neural networks as a function of their depth, width and type of activation units has been an important question in deep learning theory. Recently, depth separation results for ReLU networks were obtained via a new…

Machine Learning · Computer Science 2020-07-21 Vaggos Chatziafratis , Sai Ganesh Nagarajan , Ioannis Panageas

Ensembles over neural network weights trained from different random initialization, known as deep ensembles, achieve state-of-the-art accuracy and calibration. The recently introduced batch ensembles provide a drop-in replacement that is…

Machine Learning · Computer Science 2021-01-11 Florian Wenzel , Jasper Snoek , Dustin Tran , Rodolphe Jenatton

Over past few years afterward the birth of ResNet, skip connection has become the defacto standard for the design of modern architectures due to its widespread adoption, easy optimization and proven performance. Prior work has explained the…

Machine Learning · Computer Science 2023-03-03 Dengsheng Chen , Jie Hu , Wenwen Qiang , Xiaoming Wei , Enhua Wu

Prompt tuning is one of the successful approaches for parameter-efficient tuning of pre-trained language models. Despite being arguably the most parameter-efficient (tuned soft prompts constitute <0.1% of total parameters), it typically…

Computation and Language · Computer Science 2023-05-09 Anastasia Razdaibiedina , Yuning Mao , Rui Hou , Madian Khabsa , Mike Lewis , Jimmy Ba , Amjad Almahairi

While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception. We show that the main reason for this is the Lyapunov stability of the gradient descent…

Machine Learning · Computer Science 2018-03-23 Kamil Nar , Shankar Sastry

Randomly initialized neural networks induce a prior over functions, but the predictor used in practice is produced only after training. We ask how much of this initial bias survives the training pipeline. To make the question measurable, we…

Machine Learning · Computer Science 2026-05-29 Mohua Das , Pierfrancesco Beneventano , Shibshankar Dey , Gareth H. McKinkey , Tomaso Poggio