Shapeshifter: a parameter-efficient transformer using factorized reshaped matrices
Abstract Language models employ a very large number of trainable parameters. Despite
being highly overparameterized, these networks often achieve good out-of-sample test …
being highly overparameterized, these networks often achieve good out-of-sample test …
TT-GNN: Efficient On-Chip Graph Neural Network Training via Embedding Reformation and Hardware Optimization
Z Qu, D Niu, S Li, H Zheng, Y ** for Tensorized Neural Network Processing
The continuous growth of deep neural network model size and complexity hinders the
adoption of large models in resource-constrained platforms. Tensor decomposition has …
adoption of large models in resource-constrained platforms. Tensor decomposition has …
Tensor Network-Based Lightweight Energy Forecasting for Virtual Power Plant
Virtual power plant (VPP) operations demand lightweight energy forecasting models due to
increasing computational requirements. This paper applies tensor-train (TT) decomposition …
increasing computational requirements. This paper applies tensor-train (TT) decomposition …
[BOOK][B] Addressing Data Explosion Issue in Emerging Deep Learning Applications
Z Qu - 2023 - search.proquest.com
With the continuous booming development of deep learning, many kinds of model variants
are being proposed to tackle more difficult machine learning tasks, such as Transformers …
are being proposed to tackle more difficult machine learning tasks, such as Transformers …
Multivariate Analysis and Machine Learning towards Security Applications
Y Shin - 2022 - search.proquest.com
Analyzing the high-dimensional dataset is crucial for recent security applications. However,
detecting anomalies from practical physical systems is a challenging task due to their huge …
detecting anomalies from practical physical systems is a challenging task due to their huge …