Introduction to Machine Learning: Concepts and Applications, Lecture notes of Introduction to Machine Learning

Download Introduction to Machine Learning: Concepts and Applications and more Lecture notes Introduction to Machine Learning in PDF only on Docsity!

Introduction to Machine Learning

Tough concepts made intuitive

Agenda

Intro to ML (Machine Learning):

– Supervised Learning Use Cases (Regression,

Classification)

– Unsupervised Learning Use Cases (Clustering &

Retrieval, Recommendation, Image recognition with

Neural Networks…)

– Formalizing an ML Problem

– Data Exploration & Preparation: data issues

What is Machine Learning?

ML is a set of AI techniques

where “intelligence” is built

from examples

A set of Algorithms that can

improve as they are exposed to

more data

Vocabulary

Input (explanatory variables) &

Output (dependent variable or

target): data point

Model

Training Data (or Learn)

Features (I.e: size, number of

rooms, location…)

Predict or Score

Defining the right ML problem

Which type of e-mail is this? Spam or Not =>

Classification (with Confidence X%)

How much is this house worth? => Regression

ML is used by many companies to get more

customers or serve customers better:

Amazon (optimize price), Gmail (spam filtering),

Zillow (realestate price)….

Data exploration

Significant proportion of an analytical project

(90% of the project time)

Might be selected from multiple sources

Very important to understand (Correlations,

General trends, Outliers ...) before blindly

throwing algorithms at it

May include producing statistics (mean,

median, ...) and visualizations

Exploring Data

we notice a few things.

• There seems to be an outlier with around 800 shares and a little over 5000 likes. This might be an interesting post to investigate.
• most of our data are between 0 - 200 shares and 0 - 2000 likes, quite densely actually

Cleaning Data

some of data might not exist. In this case, we have to decide what we should do. There are many valid options:

• forget/remove the nonexistent data,
• replace it with a default value,
• interpolate (for time-series data), etc. In our case, we're just substituting a reasonable value (zero).

Use Case1: Predictive Analytics

Regression Model

To predict the price of your house: plot recent

sales of similar houses in your neighborhood

Fit a line through the data

Y= f

w

(x)=w

0

+w

1

x

x: feature, y: observation or response

w (w 0 , w 1 ) parameters of model

Find the best line by minimizing

RSS=Sum ([$house-Y]^2 )

Classification Main Concepts

Decision Trees

Confusion Matrix

Confusion Matrix

“Precision”: Fraction of positive

predictions that are actually

positive

What fraction of positive were

missed out?

“Recall”: Proportion of positive

objects that were indeed detected

as positive by the model

Precision = TP/ (TP+FP)

Recall= TP/(TP+FN)

Negatives are empty, positives are full

Use Case3: Document Retrieval

Use Case4: Product Recommendation