Search Results for author:
Found 9 papers, 1 papers with code
Efficient Training Under Limited Resources
Training time budget and size of the dataset are among the factors affecting the performance of a Deep Neural Network (DNN).
Training Integer-Only Deep Recurrent Neural Networks
Recurrent neural networks (RNN) are the backbone of many text and speech applications.
Demystifying and Generalizing BinaryConnect
BinaryConnect (BC) and its many variations have become the de facto standard for neural network quantization.
iRNN: Integer-only Recurrent Neural Network
Deploying RNNs that include layer normalization and attention on integer-only arithmetic is still an open problem.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Batch Normalization in Quantized Networks
Implementation of quantized neural networks on computing hardware leads to considerable speed up and memory saving.
Adaptive Binary-Ternary Quantization
Ternary quantization provides a more flexible model and outperforms binary quantization in terms of accuracy, however doubles the memory footprint and increases the computational cost.
How Does Batch Normalization Help Binary Training?
Binary Neural Networks (BNNs) are difficult to train, and suffer from drop of accuracy.
Differentiable Mask for Pruning Convolutional and Recurrent Networks
Pruning is one of the most effective model reduction techniques.
Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks
Using a quasiconvex base function in order to construct a binary quantizer helps training binary neural networks (BNNs) and adding noise to the input data or using a concrete regularization function helps to improve generalization error.
