Search Results for author:
Found 12 papers, 6 papers with code
Fast Block Linear System Solver Using Q-Learning Schduling for Unified Dynamic Power System Simulations
The simulation on some large power systems shows that our solver is 2-6 times faster than KLU, which is the state-of-the-art sparse solver for circuit simulation problems.
Learning the Markov Decision Process in the Sparse Gaussian Elimination
Our study is the first step to connect these two classical mathematical models: Gaussian Elimination and Markov Decision Process.
An iterative K-FAC algorithm for Deep Learning
This CG-FAC method is matrix-free, that is, no need to generate the FIM matrix, also no need to generate the Kronecker factors A and G. We prove that the time and memory complexity of iterative CG-FAC is much less than that of standard K-FAC algorithm.
A short note on the decision tree based neural turing machine
Differentiable forest is actually decision tree based neural turing machine.
Attention augmented differentiable forest for tabular data
So TAB block would learn the importance of each tree and adjust its weight to improve accuracy.
Learning Unsplit-field-based PML for the FDTD Method by Deep Differentiable Forest
The deep differentiable forest (DDF) model is introduced to replace the conventional perfectly matched layer (PML) ABC during the computation process of FDTD.
Deep differentiable forest with sparse attention for the tabular data
We present a general architecture of deep differentiable forest and its sparse attention mechanism.
LiteMORT: A memory efficient gradient boosting tree system on adaptive compact distributions
In many cases, it only need the data source itself and no extra memory.
Express Wavenet -- a low parameter optical neural network with random shift wavelet pattern
Express Wavenet is an improved optical diffractive neural network.
An optical diffractive deep neural network with multiple frequency-channels
Diffractive deep neural network (DNNet) is a novel machine learning framework on the modulation of optical transmission.
A novel guided deep learning algorithm to design low-cost SPP films
So the the cost of predicted structure is much lower than standard deep CNN.
