CritDNN
Critical dynamics improve performance in deep learning
Dohare 2024, Loss of plasticity in deep continual learning
Dohare 2024, Loss of plasticity in deep continual learning
The pervasive problem of artificial neural networks losing plasticity in continual-learning settings is demonstrated and a simple solution called the continual backpropagation algorithm is described to prevent this issue.
Storm 2024, Finite-time Lyapunov exponents of deep neural networks
Storm 2024, Finite-time Lyapunov exponents of deep neural networks
Glorot 2010, Understanding the difficulty of training deep feedforward neural networks
Glorot 2010, Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multi-layer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with experimental resul...
Langton 1990, Computation at the edge of chaos
Langton 1990, Computation at the edge of chaos
Computational Neurology
Computational Neurology
Computational Neurology Lab at Berlin Institute of Health at Charité - Universitätsmedizin Berlin
View on mobile
