随笔分类 - 技术
1
About Salary
摘要：1. Different types of neurons Linear neurons Binary threshold neurons Recitified linear neurons sigmoid neurons Stochastic binary neurons 2. Reinforce
阅读全文
摘要：1. Subplots Output: 2 .Histogram Output: Output： 3. Box plots Output: 4. Heartmap Output: 5. Animation Output: 6. Interactivity Mousing clickigng Outp
阅读全文
摘要：1. Matplotlib Backend Layer Deals with th e rendering of plots to screen or files In jupyter notebooks, we use the inline backend Artist Layer Contain
阅读全文
摘要：1. Reading csv File 2. Dates and times demo # Numpy introduction Output 1 [1 2 3] 2 (2L, 3L) 3 4 The use of arange: 5 [ 0 2 4 6 8 10 12 14 16 18 20 22
阅读全文
摘要：1. Hierarchical clustering Avoid choosing number of clusters beforehand Dendrograms help visualize different clustering granularities (no need to reru
阅读全文
摘要：1. Mixed membership model This model wants to discover a set of memberships In contrast, cluster models aim at discovering a single membership In clus
阅读全文
摘要：1. Probabilistic clustering model (k-means) Hard assignments do not tell the full story, capture the uncertainty k-means only considers the cluster ce
阅读全文
摘要：,1.One nearest neighbor Input: Query article: Xq Corpus of documents (N docs): (X1, X2, X3,... ,XN) output : XNN = min disance(Xq, Xi) 2. K-NN Algorit
阅读全文
摘要：1. Precisoin and recall precision is how precise i am at showing good stuff on my website recall is how good i am at find all the postive reviews prec
阅读全文
摘要：1. Ensemble classifier Each classifier votes on prediction Ensemble model = sign(w1f1(xi) + w2f2(xi) + w3f3(xi)) w1 w2 w3 is the learning coefficients
阅读全文
摘要：1. Quality metric Quality metric for the desicion tree is the classification error error=number of incorrect predictions / number of examples 2. Greed
阅读全文
摘要：1. Linear classifier It will use training data to learn a weight or coefficient for each word. We use the gradient ascent to find the best model with
阅读全文
摘要：1. Fit locally If the true model changes much, we want to fit our function locally to different regions of the input space. 2. Scaled distance \ we pu
阅读全文
摘要：1. Feature selection Sometimes, we need to decrease the number of features Efficiency: With fewer features, we can compute quickly Interpretaility: wh
阅读全文
摘要：1. Ridge regression A way to automatically balance between bias and varaince situations and regulate overfitting when using many features. because the
阅读全文
摘要：1. Training Error Define a loss funtion like below: and the train error is defined as theaverage loss on houses in training set: and RMSE is simply th
阅读全文
摘要：1. Modeling seasonality w1 models the linear trend of the overall process. w2 models the seasonal component sinusoid with a period of 12 and you do no
阅读全文
摘要：1. Convex and concave functions Concave is the upside-down of the convex function and convex is a bow-shaped function 2. Stepsize common choice: as th
阅读全文
摘要：1. Multiple Features note:X0 is equal to 1 2. Feature Scaling Idea: make sure features are on a similiar scale, approximately a -1<Xi<1 range For exam
阅读全文
摘要：1.Linear Regression with One variable Linear Regression is supervised learning algorithm, Because the data set is given a right answer for each exampl
阅读全文
1
浙公网安备 33010602011771号