목록Artificial Intelligence/Machine Learning (21)
Code&Data Insights
[ What is Association Rule Learning? ] Association Rule Learning : Association Rule Learning is a data mining technique that discovers rules indicating the co-occurrence of two or more items. => Identifiy the relationships between items and discovers valuable rules indicating their co-occurrence. => For example, People who bought 'this stuff', they also bought 'this stuff'. | "You may also like”..
[Machine Learning] Clustering - Hierarchical Clustering | Agglomerative Hierarchical Clustering | Dendrograms
[ Hierarchical Clustering ] Hierarchical Clustering : Hierarchical clustering is a data analysis technique that groups data hierarchically based on similarity or distance - Use Euclidean distance or Manhattan distance - 2 approachs for hierarchical Clustering : 1) Agglomaerative- Top-down 2) Divisive - Bottom-up [ Agglomerative Hierarchical Clustering ] ( Agglomerative Hierarchical Clustering : ..
[Machine Learning] Classification - K-Nearest Neighbours(KNN) | Naive Bayes
[ K-Nearest Neighbours ] K Nearest Neighbors (KNN) => KNN is a supervised learning classifier, which uses proximity to make classifications or predictions about the grouping of an individual data point. How It Works? Step 1) Choose the number K of neighbors Step 2) Take the K nearst neighbors of the new data point, according to the Euclidean distance - Euclidean Distance : √((x₂ - x₁)² + (y₂ - y..
[Machine Learning] Ensemble Learning | Random Forest
[ Ensemble Learning ] Ensemble Learning : when we take multiple algorithms or the same algorithm multiple times and we put them together that results in a much more powerful version. => It helps to improve the performance and accuracy of machine learning algorithms. => Putting multiple ML algorithms together to create one bigger ML algorithm that leverages many other ML algorithms. Type of Ensem..
[Machine Learning] Linear Model - Linear Regression | Logistic Regression | Multiclass Logistic Regression | Linear Basis Function Models
Linear Model - Easy to optimize, fast training and prediction - Good Interpretability - ONLY suitable for linearly separable classes => The capacity of the linear model depends on the input dimensionality D. => VC dimensions : D + 1 for Logistic regression VC dimension? : a measure of the capacity or complexity of a hypothesis space Linear Regression - Parameter space is convex - Objective funct..
In Multiple Iinear Regression Model, there are many variables. To build a model, we need to choose right variables ! ( Using all the variables given in the data, it's NOT a good idea ) [ 5 methods of building models ] 1. All-in - Prior knowledge - Preparing for Backward Elimination 2. Backward Elimination Step 1) Select a significance level to stay in the model (ex) SL = 0.05 ----> SL = Signific..
[Machine Learning] Decision Trees | Entropy
[ Decision Trees ] Decision Tree : a type of Supervised Machine Learning where the data is continuously split according to a certain parameter(features). The tree can be explained by two entities, namely decision nodes and leaves. Decision Tree Learning Decision 1 . How to choose what feature to spilt on at each node? Decision 2. When do you stop splitting? => stopping critria - When a node is 1..
[Machine Learning] Bias and Variance | Regularization | Learning Curves
[ Bias ] Bias - the inability for machine learning method to capture the true relationship -> In linear regression, the straight line has high bias. (underfit) -> Compared to the Squiggly line, it has low variance since the sums of squares are very similar for different data set. [ Variance ] Variance : the difference in fits between data sets. It has very little bias, but high variance ! --> fi..