508 citations · 748 across the 20 of their papers we have counts for
4 papers · 1 filter
Possible Mechanisms for Neural Reconfigurability and their Implications
Thomas M. Breuel
The paper introduces a biologically and evolutionarily plausible neural architecture that allows a single group of neurons, or an entire cortical pathway, to be dynamically reconfi…
On the Convergence of SGD Training of Neural Networks
Thomas M. Breuel
Neural networks are usually trained by some form of stochastic gradient descent (SGD)). A number of strategies are in common use intended to improve SGD optimization, such as learn…
The Effects of Hyperparameters on SGD Training of Neural Networks
Thomas M. Breuel
The performance of neural network classifiers is determined by a number of hyperparameters, including learning rate, batch size, and depth. A number of attempts have been made to e…
Benchmarking of LSTM Networks
Thomas M. Breuel
LSTM (Long Short-Term Memory) recurrent neural networks have been highly successful in a number of application areas. This technical report describes the use of the MNIST and UW3 d…