Search Results for author:
Found 9 papers, 2 papers with code
INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold
We argue that using statistical data from a batch fails to capture the crucial information for each input instance in BNN computations, and the differences between statistical information computed from each instance need to be considered when determining the binary activation threshold of each instance.
Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution
We also show that adjusting the threshold values of binary activation functions results in the unbalanced distribution of the binary activation, which increases the accuracy of BNN models.
SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System
To our best knowledge, our work is the first comprehensive study of a modularized E2E multi-domain dialog system that learning from each component to the entire dialog policy for task success.
Empirical Strategy for Stretching Probability Distribution in Neural-network-based Regression
In this study, we considered the distribution error, i. e., the inconsistency of two distributions (those of the predicted values and label), as the prediction error, and proposed weighted empirical stretching (WES) as a novel loss function to increase the overlap area of the two distributions.
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations
Binary Neural Networks (BNNs) have been garnering interest thanks to their compute cost reduction and memory savings.
Zero-shifting Technique for Deep Neural Network Training on Resistive Cross-point Arrays
By using this zero-shifting method, we show that network performance dramatically improves for imbalanced synapse devices.
BitSplit-Net: Multi-bit Deep Neural Network with Bitwise Activation Function
We demonstrate that the BitSplit version of LeNet-5, VGG-9, AlexNet, and ResNet-18 can be trained to have similar classification accuracy at a lower computational cost compared to conventional multi-bit networks with low bit precision (<= 4-bit).
Neural Network-Hardware Co-design for Scalable RRAM-based BNN Accelerators
Recently, RRAM-based Binary Neural Network (BNN) hardware has been gaining interests as it requires 1-bit sense-amp only and eliminates the need for high-resolution ADC and DAC.
Deep Neural Network Optimized to Resistive Memory with Nonlinear Current-Voltage Characteristics
Artificial Neural Network computation relies on intensive vector-matrix multiplications.
