Supervised learning vs. Unsupervised learning

AI: Sure, I can explain the difference between Supervised learning and Unsupervised learning in Machine learning.

Supervised learning is a type of machine learning where the model is trained on a labeled dataset. In other words, the dataset used to train the model has both input and output labels. The model is then trained to learn the mapping function that maps the input to the output. Once the model is trained, it can be used to predict the output for new input data.

On the other hand, unsupervised learning is a type of machine learning where the model is trained on an unlabeled dataset. In this case, the input data is not labeled, and the model is trained to find patterns and relationships in the data without any specific guidance. The goal of unsupervised learning is to identify the underlying structure in the data.

Supervised learning (MLPP 1.2)

Classification

• The goal is to learn a mapping from inputs $x$ to outputs $y$, where $y \in \{1,...,C\}$, with $C$ being the number of classes.
  • If C=2, binary classification
  • If C>2, multiclass classification
  • and labels are not mutually exclusive, multi-label classification
• Function approximation: $y=f(x) \rightarrow \hat y = \hat f(x)$

Regression

• Regression is just like classification except the response variable is continuous.

• Given $(x_1,y_),...,(x_n,y_n); x \in \R^d, y \in \R$, learn a function $f(x):x\rightarrow y$

• Simple Linear Regression

  $y=ax+b$

• Multiple (multivariate) Linear Regression

  $y=\mathbf{a}^\top \mathbf x + b$

• General Linear Regression

  $\mathbf y = A \mathbf x+ \mathbf b \iff Y=XA$

Performance Measure

• Loss function

  • L1, L2

• Gradient Descent

  $w^{k+1}=w^k-\alpha \nabla_wl(w^k)$

  $l(w_0,w_1)=\sum_i|y_i-w_i-w_0|^2_2$

  • Stochastic Gradient Descent

ML development pipeline

1. Data Preparation
2. Model specification: architecture, loss function