shanshuizui-优快云博客

转载 Deep learning 网址

http://deeplearning.net/tutorial/contents.html

2016-08-01 13:33:06 361

转载 BP神经网络模型与学习算法

一，什么是BP"BP（Back Propagation）网络是1986年由Rumelhart和McCelland为首的科学家小组提出，是一种按误差逆传播算法训练的多层前馈网络，是目前应用最广泛的神经网络模型之一。BP网络能学习和存贮大量的输入-输出模式映射关系，而无需事前揭示描述这种映射关系的数学方程。它的学习规则是使用最速下降法，通过反向传播来不断调整网络的权值和阈值，使网络的误差平方和最小

2016-08-01 10:03:30 451

原创 mx-memonger

https://github.com/dmlc/mxnet-memonger

2016-04-22 10:10:53 1337

原创 Kronecker product

If A is an m × n matrix andB is a p × q matrix, then the Kronecker productA ⊗ B is the mp × nq block matrix:more explicitly:<img class="mwe-math-fallback-image-inline tex" alt="{\mat

2016-04-22 09:48:14 2029

原创 meshgrid

>> meshgrid(1:2,1:3)ans = 1 2 1 2 1 2>> meshgrid(1:3,1:2)ans = 1 2 3 1 2 3>> meshgrid(1:3,4:5)ans = 1 2 3 1

2016-04-22 09:35:20 667

原创 MATLAB im2colstep

A=[1:3;4:6;7:9;10:12]A = 1 2 3 4 5 6 7 8 9 10 11 12>> B=im2colstep(A,[2 2])B = 1 4 7 2 5 8 4 7 10

2016-04-22 09:29:11 3458 1

原创 RCNN

http://karpathy.github.io/2015/05/21/rnn-effectiveness/

2016-04-22 09:07:50 253

原创 object detection

https://github.com/kjw0612/awesome-deep-vision#imagenet-classification ，一块求交流

2016-04-22 09:04:06 265

转载 LeNet: the MNIST Classification Model

We will assume that you have Caffe successfully compiled. If not, please refer to the Installation page. In this tutorial, we will assume that your Caffe installation is located at CAFFE_ROOT.Pr

2016-03-14 16:19:25 461