Gaussian quadrature for kernel features
Kernel methods have recently attracted resurgent interest, showing performance competitive
with deep neural networks in tasks such as speech recognition. The random Fourier features …
with deep neural networks in tasks such as speech recognition. The random Fourier features …
Low-precision random Fourier features for memory-constrained kernel approximation
We investigate how to train kernel approximation methods that generalize well under a
memory budget. Building on recent theoretical work, we define a measure of kernel …
memory budget. Building on recent theoretical work, we define a measure of kernel …
[图书][B] Kernel approximation methods for speech recognition
A May - 2018 - search.proquest.com
Over the past five years or so, deep learning methods have dramatically improved the state
of the art performance in a variety of domains, including speech recognition, computer …
of the art performance in a variety of domains, including speech recognition, computer …
Kernel approximation methods for speech recognition
We study the performance of kernel methods on the acoustic modeling task for automatic
speech recognition, and compare their performance to deep neural networks (DNNs). To …
speech recognition, and compare their performance to deep neural networks (DNNs). To …
[图书][B] Understanding and Optimizing the Statistical Performance of Machine Learning Models Under Memory Budgets
J Zhang - 2019 - search.proquest.com
Abstract Machine learning models are trending larger to attain state-of-the-art performance
across various application domains. These state-of-the-art models can consume large …
across various application domains. These state-of-the-art models can consume large …