Sciweavers

JMLR
2012
11 years 7 months ago
Krylov Subspace Descent for Deep Learning
In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In ou...
Oriol Vinyals, Daniel Povey
ICASSP
2011
IEEE
12 years 8 months ago
Linear precoding for time-varying MIMO channels with low-complexity receivers
This paper considers linear precoding for time-varying multipleinput multiple-output (MIMO) channels. We show that linear minimum mean-squared error (LMMSE) equalization based on ...
Jun Tong, Peter J. Schreier, Steven R. Weller, Lou...
INFORMATICALT
1998
105views more  INFORMATICALT 1998»
13 years 4 months ago
Parallel Implementation of a Generalized Conjugate Gradient Algorithm
This paper presents a parallel version of a Generalized Conjugate Gradient algorithm proposed by Liu and Story in which the search direction considers the effect of the inexact lin...
Jonas Koko, Aziz Moukrim
IJIT
2004
13 years 6 months ago
Modeling of Pulping of Sugar Maple Using Advanced Neural Network Learning
This paper reports work done to improve the modeling of complex processes when only small experimental data sets are available. Neural networks are used to capture the nonlinear un...
W. D. Wan Rosli, Z. Zainuddin, R. Lanouette, S. Sa...
IJCAI
2007
13 years 6 months ago
Kernel Conjugate Gradient for Fast Kernel Machines
We propose a novel variant of the conjugate gradient algorithm, Kernel Conjugate Gradient (KCG), designed to speed up learning for kernel machines with differentiable loss functio...
Nathan D. Ratliff, J. Andrew Bagnell
DAC
2005
ACM
13 years 6 months ago
Partitioning-based approach to fast on-chip decap budgeting and minimization
This paper proposes a fast decoupling capacitance (decap) allocation and budgeting algorithm for both early stage decap estimation and later stage decap minimization in today’s ...
Hang Li, Zhenyu Qi, Sheldon X.-D. Tan, Lifeng Wu, ...
ARC
2008
Springer
115views Hardware» more  ARC 2008»
13 years 6 months ago
A High Throughput FPGA-based Floating Point Conjugate Gradient Implementation
As Field Programmable Gate Arrays (FPGAs) have reached capacities beyond millions of equivalent gates, it becomes possible to accelerate floating-point scientific computing applica...
Antonio Roldao Lopes, George A. Constantinides
GLOBECOM
2009
IEEE
13 years 7 months ago
Iterative Versus Adaptive Equalizers in Time-Variant Channels
—This paper discusses the application of iterative versus adaptive equalizers to a Universal Mobile Telecommunications System (UMTS) High Speed Downlink Packet Access (HSDPA) rec...
Clemens Buchacher, Joachim Wehinger, Mario Huemer
ICANN
2001
Springer
13 years 9 months ago
Fast Curvature Matrix-Vector Products
The method of conjugate gradients provides a very effective way to optimize large, deterministic systems by gradient descent. In its standard form, however, it is not amenable to ...
Nicol N. Schraudolph