代码搜索：Learning
找到约 5,352 项符合「Learning」的源代码
代码结果 5,352
www.eeworm.com/read/429426/1948904
py knnlearner.py
# Description: Shows how to use the nearest-neighbour learning
# Category: learning
# Classes: kNNLearner, kNNClassifier, ExamplesDistance, ExamplesDistanceConstructor
# Uses: iris
#
www.eeworm.com/read/144627/12779674
c path.c
#include
#include
#include
#include "path.h"
#include "misc.h"
#include "gaussian.h"
/* path global variables (for speed) */
int deterministic;
in
www.eeworm.com/read/230098/14306139
cpp cmac.cpp
/* Reinforcement Learning
Implementation of CMAC funcltion approximation
In this implementation, function CMAC::learn(...) implements
learning using eligibility traces. There are functions
i
www.eeworm.com/read/388876/8569617
py simple_train.py
#!/usr/bin/python
import fann
connection_rate = 1
learning_rate = 0.7
num_input = 2
num_neurons_hidden = 4
num_output = 1
desired_error = 0.0001
max_iterations = 100000
iterations_between_reports =
www.eeworm.com/read/459924/7262673
py simple_train.py
#!/usr/bin/python
from pyfann import libfann
connection_rate = 1
learning_rate = 0.7
num_input = 2
num_neurons_hidden = 4
num_output = 1
desired_error = 0.0001
max_iterations = 100000
ite
www.eeworm.com/read/159921/10587914
m unsudemo.m
function []=unsudemo(action,hfigure,varargin)
% UNSUDEMO demo on unsupervised (EM) learning algorithm.
%
% UNSUDEMO demonstrates the unsupervised (Expectation-Maximization)
% learning algorithm on
www.eeworm.com/read/421949/10676604
m unsudemo.m
function []=unsudemo(action,hfigure,varargin)
% UNSUDEMO demo on unsupervised (EM) learning algorithm.
%
% UNSUDEMO demonstrates the unsupervised (Expectation-Maximization)
% learning algorithm on
www.eeworm.com/read/128468/14295412
m unsudemo.m
function []=unsudemo(action,hfigure,varargin)
% UNSUDEMO demo on unsupervised (EM) learning algorithm.
%
% UNSUDEMO demonstrates the unsupervised (Expectation-Maximization)
% learning algorithm on
www.eeworm.com/read/215139/15073048
m rsomhebbv01.m
function Net = RSOMHebbV01(Net , I , RSOMState , WinnerInd)
% RSOMHebbV01 Hebbian learning for RSOM network with learning rates
% decay.
%
% ---------------------------------