Pages that link to "Item:Q5059670"
From MaRDI portal
The following pages link to Mean-field inference methods for neural networks (Q5059670):
Displaying 12 items.
- Hidden unit specialization in layered neural networks: ReLU vs. sigmoidal activation (Q2068413) (← links)
- A Riemannian mean field formulation for two-layer neural networks with batch normalization (Q2157932) (← links)
- A gradient flow formulation for the stochastic Amari neural field model (Q2330609) (← links)
- Advanced mean field methods. Theory and practice (Q2736595) (← links)
- Model-independent mean-field theory as a local method for approximate propagation of information (Q4240817) (← links)
- On Langevin Updating in Multilayer Perceptrons (Q4323333) (← links)
- Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification* (Q5020049) (← links)
- Align, then memorise: the dynamics of learning with feedback alignment* (Q5049525) (← links)
- Align, then memorise: the dynamics of learning with feedback alignment* (Q5055410) (← links)
- Mean Field Analysis of Deep Neural Networks (Q5076694) (← links)
- Mean Field Approximation for Fields of Experts (Q5417549) (← links)
- A dynamical mean-field theory for learning in restricted Boltzmann machines (Q5857421) (← links)
