[HTML][HTML] Evolving artificial neural networks with feedback
S Herzog, C Tetzlaff, F Wörgötter - Neural Networks, 2020 - Elsevier
Neural networks in the brain are dominated by sometimes more than 60% feedback
connections, which most often have small synaptic weights. Different from this, little is known …
connections, which most often have small synaptic weights. Different from this, little is known …
Nonlinear systems identification using deep dynamic neural networks
Neural networks are known to be effective function approximators. Recently, deep neural
networks have proven to be very effective in pattern recognition, classification tasks and …
networks have proven to be very effective in pattern recognition, classification tasks and …
Dropneuron: Simplifying the structure of deep neural networks
Deep learning using multi-layer neural networks (NNs) architecture manifests superb power
in modern machine learning systems. The trained Deep Neural Networks (DNNs) are …
in modern machine learning systems. The trained Deep Neural Networks (DNNs) are …
On warm-starting neural network training
In many real-world deployments of machine learning systems, data arrive piecemeal. These
learning scenarios may be passive, where data arrive incrementally due to structural …
learning scenarios may be passive, where data arrive incrementally due to structural …
Globally gated deep linear networks
Q Li, H Sompolinsky - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Abstract Recently proposed Gated Linear Networks (GLNs) present a tractable nonlinear
network architecture, and exhibit interesting capabilities such as learning with local error …
network architecture, and exhibit interesting capabilities such as learning with local error …
The neural network zoo
S Leijnen, F Veen - Proceedings, 2020 - mdpi.com
An overview of neural network architectures is presented. Some of these architectures have
been created in recent years, whereas others originate from many decades ago. Apart from …
been created in recent years, whereas others originate from many decades ago. Apart from …
Stfnets: Learning sensing signals from the time-frequency perspective with short-time fourier neural networks
Recent advances in deep learning motivate the use of deep neural networks in Internet-of-
Things (IoT) applications. These networks are modelled after signal processing in the …
Things (IoT) applications. These networks are modelled after signal processing in the …
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
Despite the widespread practical success of deep learning methods, our theoretical
understanding of the dynamics of learning in deep neural networks remains quite sparse …
understanding of the dynamics of learning in deep neural networks remains quite sparse …
Dynamic deep neural networks: Optimizing accuracy-efficiency trade-offs by selective execution
Abstract We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward
deep neural network that allows selective execution. Given an input, only a subset of D2NN …
deep neural network that allows selective execution. Given an input, only a subset of D2NN …
Closed-form continuous-time neural networks
Continuous-time neural networks are a class of machine learning systems that can tackle
representation learning on spatiotemporal decision-making tasks. These models are …
representation learning on spatiotemporal decision-making tasks. These models are …