paper-with-me

Papers

Meta-Learning Bidirectional Update Rules

2021-04-10 · Mark Sandler, Max Vladymyrov, Andrey Zhmoginov, Nolan Miller, Andrew Jackson, Tom Madams, Blaise Aguera y Arcas

In this paper, we introduce a new type of generalized neural network where neurons and synapses maintain multiple states. We show that classical gradient-based backpropagation in neural networks can be seen as a special case of a two-state network where one state is used for activations and another for gradients, with update rules derived from the chain rule. In our generalized framework, networks have neither explicit notion of nor ever receive gradients. The synapses and neurons are updated using a bidirectional Hebb-style update rule parameterized by a shared low-dimensional "genome". We show that such genomes can be meta-learned from scratch, using either conventional optimization techniques, or evolutionary strategies, such as CMA-ES. Resulting update rules generalize to unseen tasks and train faster than gradient descent based optimizers for several standard computer vision and synthetic tasks.

📄 PDF Abstract BibTeX arXiv:2104.04657

Code (1)

google-research/google-research/tree/master/blur 공식 구현 jax

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

MTL2L: A Context Aware Neural Optimiser

2020-07-18 · Nicholas I-Hsien Kuo, Mehrtash Harandi, Nicolas Fourrier, Christian Walder 외

Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner. Previously, it was shown that a meta-learner could learn the direct rules to update learner parameters; and that the l…

Multi-Task Learning

Meta-Learning Parameterized First-Order Optimizers using Differentiable Convex Optimization

2023-03-29 · Tanmay Gautam, Samuel Pfrommer, Somayeh Sojoudi

Conventional optimization methods in machine learning and controls rely heavily on first-order update rules. Selecting the right method and hyperparameters for a particular task often involves trial-and-error or practiti…

Meta-Learning

Celo2: Towards Learned Optimization Free Lunch

2026-02-22 · Abhinav Moudgil, Boris Knyazev, Eugene Belilovsky arxiv

Learned optimizers are powerful alternatives to hand-designed update rules like Adam, yet they have seen limited practical adoption since they often fail to meta-generalize beyond their training distribution and incur hi…

Meta-learning three-factor plasticity rules for structured credit assignment with sparse feedback

2025-12-10 · Dimitra Maoutsa arxiv

Biological neural networks learn complex behaviors from sparse, delayed feedback using local synaptic plasticity, yet the mechanisms enabling structured credit assignment remain elusive. In contrast, artificial recurrent…

Evolving Neural Update Rules for Sequence Learning

2021-09-29 · Karol Gregor, Peter Conway Humphreys

We consider the problem of searching, end to end, for effective weight and activation update rules governing online learning of a recurrent network on problems of character sequence memorisation and prediction. We experi…