deep learning 学习笔记
来源:互联网 发布:python twisted 安装 编辑:程序博客网 时间:2024/04/26 21:37
link: http://ufldl.stanford.edu/tutorial/
1. linear regression
use MLE to understand the loss function
2. logistic regression— binary classification
use MLE to understand the loss function
3. softmax regression —multiple classification
4. Neural Network
activation function: sigmod(0,1), tanh[-1,1], rectified linear(0,+inf)
forward propagation
用input feature x 通过activation function 来计算最后输出的prediction结果的过程
backpropagation algorithm
整个NN也是算一个loss function 再用batch gradient descent 来计算W和b就行。只是在求
这里partial derivative是每个training sample的partial derivative的和,就是说没求一次partial derivative 就要scan所有的training sample
Supervised CNN
feature extraction by convolution
当input 的sample 的维度extremely large, we can firstly apply convolution降维, 然后利用pooling降维
SGD
compared with the batch GD. just use a single training example or a small amount of examples called “minibatch”, ususally 256.
notice the the term “minibatch”, “epoch”(iteration over the whole data set), “shuffle”
One final but important point regarding SGD is the order in which we present the data to the algorithm. If the data is given in some meaningful order, this can bias the gradient and lead to poor convergence. Generally a good method to avoid this is to randomly shuffle the data prior to each epoch of training.
Momentum
If the objective has the form of a long shallow ravine leading to the optimum and steep walls on the sides, standard SGD will tend to oscillate across the narrow ravine since the negative gradient will point down one of the steep sides rather than along the ravine towards the optimum. The objectives of deep architectures have this form near local optima and thus standard SGD can lead to very slow convergence particularly after the initial steep gains. Momentum is one method for pushing the objective more quickly along the shallow ravine.
这里就是说如果objective function是一个很陡的谷底,那么每次update都很容易从谷的一边跑到另外一边,即在谷内震荡下行。
Note
filter / kernel: for example, it is the 8*8 patch for convolution
after convolution, we get feature map.
CNN consists of three parts.
normal fully connected NN layers in CNN.
subsampling layer is the pooling layer in CNN.
convolutional layer in CNN
Comparison
对比普通NN, CNN就是可以利用convolution and pooling 处理高维的输入数据
Sparse coding && PCA
ICA && RICA
unsupervised learning
autoencoder
feature extraction for unsupervised learning when we don’t have the trained labels.
Statistical Language Modeling (SLM)
ref: http://homepages.inf.ed.ac.uk/lzhang10/slm.html
definition
probabilistic chain rule
RNN
ref: http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/
http://karpathy.github.io/2015/05/21/rnn-effectiveness/
definition
The idea behind RNNs is to make use of sequential information. In a traditional neural network we assume that all inputs (and outputs) are independent of each other. But for many tasks that’s a very bad idea.
i.e. RNN considers the dependency of the training samples. In other words, each training sample has somewhat dependency or sequential relationship
note
the ref (http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-2-implementing-a-language-model-rnn-with-python-numpy-and-theano/) wildml has provided a specific implementation example.
several issues should be noted:
1.在generating text的code中
next_word_probs = model.forward_propagation(new_sentence)
这里其实是用的theano中的forward_propagation,不是作者自己写的forward_propagation.
while sampled_word == word_to_index[unknown_token]: samples = np.random.multinomial(1, next_word_probs[-1]) sampled_word = np.argmax(samples)
所以这里next_word_probs[-1] 其实是表示的o[-1],对应input x的最后一个word,然后samples就是一个one-hot-vector,再用np.argmax取得index。
LSTM
a type of RNN can capture a long dependency
只是为了克服RNN cannot capture the long dependency的问题。
只是计算
loss function
least mean square
cross-entropy loss, i.e. log loss function or logistic loss
Backpropagation Alg.
http://cs231n.github.io/optimization-1/
http://colah.github.io/posts/2015-08-Backprop/
http://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/
内含推导BP公式过程
https://theclevermachine.wordpress.com/2014/09/06/derivation-error-backpropagation-gradient-descent-for-neural-networks/
注意
computational graph
forward-mode differentiation,一次只能计算output对其中一个input的偏导数,即如果在computational graph 中input很多,那么这种方法计算偏导数就会很慢。求从其中一条input到output所有的path的
reverse-mode differentiation 更快,可以一次性计算 output对所有的node的偏导数,就是backpropagation.
- deep learning 学习笔记
- Deep Learning 学习笔记
- Deep Learning 学习笔记
- 【deep learning学习笔记】Autoencoder
- Deep Learning(学习笔记)
- Deep Learning 学习笔记一
- deep learning学习笔记---MemN2N
- 机器学习笔记-Deep Learning
- 【Deep Learning学习笔记】Deep learning for nlp without magic_Bengio_ppt_acl2012
- 笔记 | 吴恩达Coursera Deep Learning学习笔记
- 笔记 | 吴恩达Coursera Deep Learning学习笔记
- Deep Learning(深度学习)学习笔记
- Deep Learning(深度学习)学习笔记
- 深度学习deep learning学习笔记
- Deep Learning(深度学习)学习笔记
- Deep Learning(深度学习)学习笔记
- Deep Learning与自然语言处理学习笔记
- Deep Learning学习笔记——1
- ios开发大连讯飞语音sdk
- 《剑指offer》——整数中1出现的次数(从1到n整数中1出现的次数)
- 内存泄露从入门到精通三部曲之常见原因与用户实践
- AsyncTask 异步任务
- HDOJ 2049 不容易系列之(4)——考新郎【错排 组合数】
- deep learning 学习笔记
- SSH三大框架整合步骤
- Android连接服务器的封装类
- 如何在Mac OS X上安装 Ruby运行环境
- 进程线程及堆栈关系的总结 http://blog.csdn.net/echoisland/article/details/6403763
- UI - UIDatePicker
- poj 3660 传递性关系 floyd更新
- leetcode 62:Unique Paths
- iOS新技术和学习网站