paper-with-me

Papers

HyperNetworks

2016-09-27 · David Ha, Andrew Dai, Quoc V. Le

This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in nature: the relationship between a genotype - the hypernetwork - and a phenotype - the main network. Though they are also reminiscent of HyperNEAT in evolution, our hypernetworks are trained end-to-end with backpropagation and thus are usually faster. The focus of this work is to make hypernetworks useful for deep convolutional networks and long recurrent networks, where hypernetworks can be viewed as relaxed form of weight-sharing across layers. Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks. Our results also show that hypernetworks applied to convolutional networks still achieve respectable results for image recognition tasks compared to state-of-the-art baseline models while requiring fewer learnable parameters.

📄 PDF Abstract BibTeX arXiv:1609.09106

Code (10)

cellistigs/ensemble_attention pytorch
chrhenning/hypnettorch pytorch
g1910/HyperNetworks pytorch
gahaalt/continual-learning-overview tf
gahaalt/continual-learning-with-hypernets tf
gtegner/hyper-gan pytorch
labmlai/annotated_deep_learning_paper_implementations pytorch
pennfranc/hypnettorch pytorch
shyamsn97/hyper-nn jax
tjuhaoxiaotian/pymarl3 pytorch

Tasks

Handwriting generationLanguage ModellingMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

HyperNetwork A HyperNetwork is a network that generates weights for a main network. The behavior of the main network is the same with any usual neural network: it learns to map some raw…

Similar Papers 제목 키워드 기반

Effect of Optimizer, Initializer, and Architecture of Hypernetworks on Continual Learning from Demonstration

2023-12-31 · Sayantan Auddy, Sebastian Bergner, Justus Piater

In continual learning from demonstration (CLfD), a robot learns a sequence of real-world motion skills continually from human demonstrations. Recently, hypernetworks have been successful in solving this problem. In this …

Continual Learning

Partial Hypernetworks for Continual Learning

2023-06-19 · Hamed Hemati, Vincenzo Lomonaco, Davide Bacciu, Damian Borth

Hypernetworks mitigate forgetting in continual learning (CL) by generating task-dependent weights and penalizing weight changes at a meta-model level. Unfortunately, generating all weights is not only computationally exp…

Continual Learning

Stochastic Maximum Likelihood Optimization via Hypernetworks

2017-12-04 · Abdul-Saboor Sheikh, Kashif Rasul, Andreas Merentitis, Urs Bergmann

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as r…

ClassificationGeneral Classificationregression

Language Modeling with Recurrent Highway Hypernetworks

2017-12-01 · NeurIPS 2017 12 · Joseph Suarez

We present extensive experimental and theoretical support for the efficacy of recurrent highway networks (RHNs) and recurrent hypernetworks complimentary to the original works. Where the original RHN work primarily provi…

Language ModelingLanguage Modelling

On Infinite-Width Hypernetworks

2020-03-27 · NeurIPS 2020 12 · Etai Littwin, Tomer Galanti, Lior Wolf, Greg Yang

{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}. A notable application of hypernetworks in the recent literature involves learning to output functional representati…

Meta-Learning