Results 1  10
of
88,791
Learning from demonstration
 Advances in Neural Information Processing Systems 9
, 1997
"... By now it is widely accepted that learning a task from scratch, i.e., without any prior knowledge, is a daunting undertaking. Humans, however, rarely attempt to learn from scratch. They extract initial biases as well as strategies how to approach a learning problem from instructions and/or demonstra ..."
Abstract

Cited by 392 (32 self)
 Add to MetaCart
By now it is widely accepted that learning a task from scratch, i.e., without any prior knowledge, is a daunting undertaking. Humans, however, rarely attempt to learn from scratch. They extract initial biases as well as strategies how to approach a learning problem from instructions and
Speedup Learning
, 2007
"... Speedup learning is a branch of machine learning that studies learning mechanisms for speeding up problem solvers based on problem solving experience. The input to a speedup learner typically consists of observations of prior problemsolving experience, which may include traces of the problem solver ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
Speedup learning is a branch of machine learning that studies learning mechanisms for speeding up problem solvers based on problem solving experience. The input to a speedup learner typically consists of observations of prior problemsolving experience, which may include traces of the problem
Image Segmentation by Data Driven Markov Chain Monte Carlo
, 2001
"... This paper presents a computational paradigm called Data Driven Markov Chain Monte Carlo (DDMCMC) for image segmentation in the Bayesian statistical framework. The paper contributes to image segmentation in three aspects. Firstly, it designs effective and well balanced Markov Chain dynamics to exp ..."
Abstract

Cited by 275 (32 self)
 Add to MetaCart
to explore the solution space and makes the split and merge process reversible at a middle level vision formulation. Thus it achieves globally optimal solution independent of initial segmentations. Secondly, instead of computing a single maximum a posteriori solution, it proposes a mathematical principle
SpeedUp Techniques for Simulation
 Telektronikk
, 1995
"... Due to increased complexity and extreme quality of service requirements, traditional means for performance evaluation of telecom networks do not always suffice. The most flexible approach has been, and still is, simulation, which is the main focus of this paper. However, severe problems regarding ef ..."
Abstract

Cited by 8 (5 self)
 Add to MetaCart
efficiency exist, e.g. evaluation of ATM cell loss rate in range of <10 9 which is very computer intensive and hardly feasible within reasonable time with direct simulation. This calls for new and more efficient simulation techniques. An overview of some speedup approaches is given. The paper also
SMARTS: Accelerating Microarchitecture Simulation via Rigorous Statistical Sampling
 in Proceedings of the 30th annual international symposium on Computer architecture
, 2003
"... Current softwarebased microarchitecture simulators are many orders of magnitude slower than the hardware they simulate. Hence, most microarchitecture design studies draw their conclusions from drastically truncated benchmark simulations that are often inaccurate and misleading. This paper presents ..."
Abstract

Cited by 256 (25 self)
 Add to MetaCart
instructions per benchmark. In practice, inaccuracy in microarchitectural state initialization introduces an additional uncertainty which we empirically bound to ~2 % for the tested benchmarks. Our implementation of SMARTS achieves an actual average error of only 0.64 % on CPI and 0.59% on EPI for the tested
Origin of the quantum speedup
, 2012
"... Bob chooses a function from a set of functions and gives Alice the black box that computes it. Alice is to
nd a characteristic of the function through function evaluations. In the quantum case, the number of function evaluations can be smaller than the minimum classically possible. The fundamental ..."
Abstract
 Add to MetaCart
outcome shows that: (i)
nding the characteristic of the function on the part of Alice is a byproduct of reconstructing Bobs choice and (ii) because of the quantum correlation between choice and reconstruction, one cannot tell whether Bobs choice is determined by the action of Bob (initial measurement
Analysis of the Speedup of Distributed Applications
"... Abstract. Speedup is one of the main performance characteristics of distributed applications. It is usually defined as the ratio of application’s execution time on a single processor to the execution time, of the same workload, on a system composed on P processors. This chapter analyzes, in very gen ..."
Abstract
 Add to MetaCart
Abstract. Speedup is one of the main performance characteristics of distributed applications. It is usually defined as the ratio of application’s execution time on a single processor to the execution time, of the same workload, on a system composed on P processors. This chapter analyzes, in very
An Algorithm for Adaptive Maximization of Speedup
, 2003
"... www.cosc.brocku.ca AN ALGORITHM FOR ADAPTIVE MAXIMIZATION OF SPEEDUP We describe an algorithm for workload evaluation and autoadaptive maximization of speedup. Emphasis is put on exploitation of medium and finegrain algorithmic parallelism. The simulation results suggest that significant speedups ..."
Abstract
 Add to MetaCart
www.cosc.brocku.ca AN ALGORITHM FOR ADAPTIVE MAXIMIZATION OF SPEEDUP We describe an algorithm for workload evaluation and autoadaptive maximization of speedup. Emphasis is put on exploitation of medium and finegrain algorithmic parallelism. The simulation results suggest that significant
Speedup Simulation Techniques
 Proc. Workshop on Rare Event Simulation
, 1997
"... This presentation gives a brief survey of speedup techniques for discrete event simulation where the quantity of interest depends on rare events to occur. Both rare event simulation approaches like RESTART/splitting and importance sampling and other complementary techniques are described. A list of ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
This presentation gives a brief survey of speedup techniques for discrete event simulation where the quantity of interest depends on rare events to occur. Both rare event simulation approaches like RESTART/splitting and importance sampling and other complementary techniques are described. A list
1. SpeedUp and Vicinity
"... Connections are shown between two properties of a machine model: linear speedup and polynomial vicinity. In the context of the author’s Block Move (BM) model, these relate to: “How long does it take to simulate a finite transducer S on a given input z? ” This question is related to the centuryold ..."
Abstract
 Add to MetaCart
Connections are shown between two properties of a machine model: linear speedup and polynomial vicinity. In the context of the author’s Block Move (BM) model, these relate to: “How long does it take to simulate a finite transducer S on a given input z? ” This question is related to the century
Results 1  10
of
88,791