Backpropagation

Feeds to Scour
SubscribedAll
Scoured 90 posts in 5.7 ms

Generalizable self-supervised learning for imaging flow cytometry on multi-dataset leukocyte differential

馃Linear Algebra + AIContent type: Academic
nature.com

Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network

馃Calculus + AIContent type: Academic
arxiv.org

Predictive Coding with Bayesian Priors via Proximal Gradients

馃幉Bayesian InferenceContent type: Academic
arxiv.org

Exploring the Design Space of Reward Backpropagation for Flow Matching

馃Linear Algebra + AIContent type: Academic
arxiv.org

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

馃Linear Algebra + AIContent type: Code
github.comHacker News

Overcoming Rank Collapse in Feedback Alignment

馃Linear Algebra + AIContent type: Academic
arxiv.org

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

馃Calculus + AIContent type: Academic
arxiv.org

Second-Order Path Kernel Interpolation Formulas in Machine Learning

馃Calculus + AIContent type: Academic
arxiv.org

Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment

馃Linear Algebra + AIContent type: Academic
arxiv.org

Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway

馃Calculus + AIContent type: Academic
arxiv.org

Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through Deep Learning

馃Calculus + AIContent type: Academic
arxiv.org

iblameandrew/open-deepthink: Grok-heavy at the price of API cost. You choose the model. An unlimited army to think about your problem.

馃Linear Algebra + AIContent type: Code
github.comr/LocalLLaMA

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

馃Linear Algebra + AIContent type: Academic
arxiv.org

A Theory on Flow Matching with Neural Networks

馃Calculus + AIContent type: Academic
arxiv.org

Theory of learning of high-dimensional controlled non-linear dynamical systems (I): models and methods

馃Calculus + AIContent type: Academic
arxiv.org

Reinforcement Learning for Flow-Matching Policies with Density Transport

馃Linear Algebra + AIContent type: Academic
arxiv.org

Variational Proximal Policy Optimization

馃幉Probability + AIContent type: Academic
arxiv.org

Learning Dynamics Reveal a Hierarchy of Weight-Induced Layerwise Gram Metrics

馃Calculus + AIContent type: Academic
arxiv.org

Symmetries and overparametrization properties of Hamiltonian variational ansatzes for the $(1+1)$d $\mathbb{Z}_2$ lattice gauge theory

馃搱OptimizationContent type: Academic
arxiv.org

Predicting Physical and Physical-Chemical Properties of Molecular-Based Materials Using Computational Neural Networks

馃Linear Algebra + AIContent type: Academic
arxiv.org
Sign up or log in to see more results

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help