Week 2 Notes


Vectors & Matrices (Monday Sept 12th, 2022)

Date 09/12/2022
Topic Vectors & Matrices
Professor Dr. John Bukowy
Week 2

Vectors in Machine Learning

Vectors

x.shape
> (3,)

# There is a distinction in numpy with dot product and such
x.shape
> (3, 1)

Examples of 2D points

Examples of 3D points

Geometric Vector

Vectors

Dot product

Euclidean Distance

Dot Products and Vector Norms

u . v = ||u|| ||v|| cos(a)
- if a > 90 then u . v < 0
- if a == 90 then u . v == 0
- if a < 90 then u . v > 0
- if a == 0 then u . v == ||u|| ||v|| and they are parallel
- if a == 180 then u . v == -||u|| ||v|| and they are anti-parallel

Matrices

Matrix-Vector Multiplication

Ab = c

Matrix-Matrix Multiplication

AB = C

Modelling (Tuesday Sept 13th, 2022)

Date 09/13/2022
Topic Modelling
Professor Dr. John Bukowy
Week 2
  1. What is a model?
  2. What is a linear model?
  3. What is a linear model for regression and classification?
  4. Advantages and disadvantages of a linear model?

(Mathematical) Models

"no model is correct, but some are useful" - Bokowy

Models Examples

Models: Input-Output Relationship

Machine Learning Models

What do linear models do?

It allows us to convert from a higher dimensional space to a scalar value. It compresses the information contained in each feature in one scalar.

How do we find the weights

Linear Regression

y = w1x1 + w0

Multiple linear Regression

Linear Classification (Binary Classification)

Non-Linear Models & Decision Boundaries (Friday Sept 16th, 2022)

Date 09/16/2022
Topic Non-Linear Models & Decision Boundaries
Professor Dr. John Bukowy
Week 2

Linear Models

Advantages/Disadvantages of Linear Models

Advantages

Disadvantages

Extending linear models

Non-Linear Models

KNN and Tree Models

Decision boundaries

Feature Scaling

Non-linear

Do we need non-linear models?