Best starting place on the web is Machine Learning on coursera. It will get you started on what Machine Learning is all about. Next try to understand topics in http://ufldl.stanford.edu/ . I think the ufldl website isn't completely edited for the new version. So, feel free to browse both old and the new versions. If you are not so great in math, I would recommend this book as a good starting point to get basic calculus used in neural networks. This is also a good starting point to understand backpropogation.
This is the order in which I studied them. If you know some of them already, feel free to skip them.
Pre-reqs to learn (try to learn the theory and how they work in practice):
- Linear regression (including square error terms, mean error terms, concept of regularlization, L1 and L2 distance).
- Gradient Descent (intuition of difference between conjugate, stochastic, mini-batch, batch/regular gradient descent). Awareness of bfgs, lbfgs optimization algorithms (you don't need to understand the details).
- Activation functions (sigmoid, tan h, ReLU) and their derivatives.
- Logistic regression (binary and multi-class classification).
- Softmax regression (multinomial logistic regression).
- Artificial Neural Networks (including feed forward back-propagation).
- SVM. (with intuition of different kernels)
- Dimensionality reduction using LDA, PCA.
- Autoencoder (including the idea of denoising autoencoder and sparse autoencoder).
- Autoencoder with linear decoder (doesn't use a sigmoid like in regular autoencoder).
- Greedy layer wise training in deep learning.
- Stacked auto-encoder (how to combine multiple autoencoders with a softmax regression final layer).
- Convolution operation, Pooling (max, mean, stochastic).
- Convolutional Neural Networks.
- Restricted Boltzman Machines.
- Deep Belief Networks.
Convolution with filters obtained from Autoencoders (unsupervised learning) help Convolutional Neural Networks in unsupervised feature learning. Sometimes, convolution filters used are simple gabor filters.
Other interesting links:
Other interesting links:
No comments:
Post a Comment