basic concept
Neural Network: NN Neural Network
Convolutional Neural Network: CNN Convolutional Neural Network
Recurrent Neural Networks: RNN Recurrent Neural Networks
Deep Neural Networks: DNN Deep Neural Networks
Natural Language Processing; NLP Natural Language Processing
Neuro-Linguistic Programming: NLP Neuro-Linguistic Programming)
Multi-layer neural network: MLP Multi-Layer Perceptron (one layer is called linear regression, many are MLP)
Three forms of gradient descent : http://www.cnblogs.com/maybe2030/p/5089753.html
Batch Gradient Descent: BGD Batch Gradient Descent
Stochastic Gradient Descent: SGD Stochastic Gradient Descent
Mini-batch gradient descent: MBGD Mini-batch Gradient Descent
Also: Momentum, Nesterov Momentum, AdaGrad, RMSProp, Adam
http://blog.csdn.net/u014595019/article/details/52989301
BP algorithm: The learning process consists of two processes of forward propagation of the signal and back propagation of the error. Because the training of the multi-layer feed-forward network often adopts the error back-propagation algorithm , people often refer to the multi-layer feed-forward network directly as the BP network. Error Back Propagation, error back propagation.
Data Set
Sample
Attribute Attribute Feature Feature
Feature Value Feature Value
The space spanned by features and samples:
Feature Space Feature Space Sample Space Sample Space Label Space Label Space
When the model is a classifier, the class space
Data set: Training Set Training Set Test Set Test Set Cross-Validation Set (CV Set)
Hypothesis space: where the model is mathematically applicable
Generalization: how well the model performs on unknown data
Datasets website: http://archive.ics.uci.edu/ml/datasets.html
Structural Risk Minimization: SRM Structural Risk Minization
The tradition is: Empirical Risk Minimization ERM Empirical Risk Minization
Three kinds of cross-validation: S-fold Cross validation (S-fold cross validation) Leave-one-out Cross Validation (Leave-one-out Cross Validation) Simple cross validation
Maximum Likelihood Estimate: ML Estimate Maximum Likelihood Estimate
Maximum Posterior Probability Estimation: MAP
Bayesian Decision Theory: Bayesian Decision Theory
Naive Bayes: Naive Bayes
Discrete Naive Bayes: MultinomialNB
Continuous Naive Bayes: GaussianNB
Mixed Naive Bayes: MergedNB