Direct Feedback Alignment With Sparse Connections for Local Learning
نویسندگان
چکیده
منابع مشابه
Direct Feedback Alignment Provides Learning in Deep Neural Networks
Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently discovered method called feedback-alignment shows that the weights used for propagating the error backward don’t have to be symmetric with the weights used for p...
متن کاملDirect Feedback Alignment Provides Learning in Deep Neural Networks
Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently discovered method called feedback-alignment shows that the weights used for propagating the error backward don’t have to be symmetric with the weights used for p...
متن کاملExtreme Learning Machine with Local Connections
This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine). For ordinary feedforward neural networks, the sparsification is usually done by introducing certain regularization technique into the learning process of the network. But this strategy can not be applied for ELM, since the input-hidden weights of ELM are supposed to be randomly chosen ...
متن کاملICA with Sparse Connections
When applying independent component analysis (ICA), sometimes we expect that the connections between the observed mixtures and the recovered independent components (or the original sources) to be sparse, to make the interpretation easier or to reduce the model complexity. In this paper we propose natural gradient algorithms for ICA with a sparse separation matrix, as well as ICA with a sparse m...
متن کاملICA with Sparse Connections: Revisited
When applying independent component analysis (ICA), sometimes we expect the connections between the observed mixtures and the recovered independent components (or the original sources) to be sparse, to make the interpretation easier or to reduce the random effect in the results. In this paper we propose two methods to tackle this problem. One is based on adaptive Lasso, which exploits the L1 pe...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Frontiers in Neuroscience
سال: 2019
ISSN: 1662-453X
DOI: 10.3389/fnins.2019.00525