WHAT IS RBM Restricted Boltzmann Machine is one of the special cases of Boltzmann Machine, which restricted all visible-visible connections and hidden-hidden connections, which makes for each hidden unit, it connects to all visible units, and for each visible unit, it connects to all hidden units. Following is a figure which shows the model of RBM.
Here’s a code for reading MNIST dataset in C++, the dataset can be found HERE, and the file format is as well. Using this code, you can read MNIST dataset into a double vector, or an OpenCV Mat, or Armadillo mat. Feel free to use it for any purpose. (part of this code is stolen from … [Read more…]
WHAT IS SOFTMAX Softmax regression always as one module in a deep learning network, and most likely to be the last module, the output module. What is it? It is a generalized version of logistic regression. Just like logistic regression, it belongs to supervised learning, and the superiority is, the class label y can be more than … [Read more…]
ABOUT UNSUPERVISED LEARNING In supervised learning problems, we deal with labeled data, means during the training process, we give our machine both Xs and Ys, by training, we ‘forge’ a system, which given new Xs, it is able to guess the output Ys. By using better algorithm and sophisticated methods, we can make the forged system … [Read more…]
I used to thought that BP Neural Networks algorithm belongs to supervised learning, however, after learned about Sparse Autoencoder algorithm, I realized it can also be used for unsupervised learning (use the unlabeled data itself as both input and output). BP neural networks is the base of a lot of other advanced neural networks algorithm, … [Read more…]
I chose Prof. Yann LeCun‘s Deep Learning as one of my three attending courses this semester, because that I have no background of machine learning, so I also viewing Prof. Andrew Ng’s Machine Learning lectures online recent days. At the beginning of the lectures, it was about linear regression. I heard about some simple linear regression … [Read more…]