Machine Learning - Foundations

Orientation

An Interactive Session

Faculty

Prof. Harish Guruprasad

Prof. Arun Rajkumar

Prof. Prashanth LA

 Machine learning,

statistical learning theory and

optimisation.

 Machine learning,

statistical learning theory with applications to education and healthcare

Reinforcement learning, simulation optimization and

multi-armed bandits

Instructors

Anamika

Abhinandan

Arun

Amrutha

Jimmi

Vishal

Do you want to understand how Machine Learning algorithms work?

So

use Machine Learning algorithms  

Almost all products from

Do you Know?

use Machine Learning algorithms  

Almost all products from

Do you Know?

Not only that, do you want to  become an expert in Machine Learning?

Sounds Great, Let's Start with

Linear Algebra

Calculus 

Probability and Statistics

What?.. No..No..

Optimisation

Nowadays, many of you might think

import numpy as np
import tensorflow as tf
import keras
import torch.nn as nn
import nltk
import sklearn
import pandas as pd

This is just a part not the whole of data science or ML!

Linear Algebra, Calculus, Optimisation

 Probability

&

Statistics

Applications

Hmm ...

Thinking of,

where it is not applied..

Engineering?

Particle Physics?

Chemistry?

Molecular Biology?

Astronomy?

Law?

Education?

Hard to find!

Pre-Requisites

  • Linear Algebra

  • Calculus 

  • Probability

Introductory level in

  • Python Programming

We review and help you understand all the required concepts.

Your interest, involvement and perseverance matters more than anything!

What will I learn in MLF?

1

Introduction to

Machine Learning

Perception

Very Easy

What will I learn in MLF?

2

Calculus 

\(\frac{d y(x_0)}{dx}\)

Perception

Easy

What will I learn in MLF?

3

Linear Algebra:

Least Square Regression

Perception

Moderate

What will I learn in MLF?

4

Linear Algebra:

Eigenvalues & Eigenvectors

Moderate

Perception

What  will I learn in MLF?

5

Linear Algebra:

Complex Matrices and SVD

Difficult

Perception

What  will I learn in MLF?

6

Linear Algebra:

PCA and its applications

Difficult

Perception

What will I learn in MLF?

7

Optimisation:

Unconstrained

Easy

Perception

What will I learn in MLF?

8

Optimisation:

Convex sets,functions

 

Moderate

Perception

What  will I learn in MLF?

9

Optimisation:

Constrained and Lagrange multipliers

Moderate

Perception

What  will I learn in MLF?

10

Probabilistic Models in Machine Learning

 

Very Easy

Perception

What will I learn in MLF?

11

Exponential Family of

Distributions

Moderate

Perception

What will I learn in MLF?

12

Parameter estimation

Expectation Maximization

Difficult

Perception

What is the Grading Policy?

Two Quizzes (50%)

Final Exam (50%)

Types of Questions:

1. MCQ

2. MSQ

3. NAT

How much effort do I need to put into per week?

3 Hours for 

watching 

Live sessions

Activity, Practice, Test

"Any unwillingness to learn mathematics today can greatly restrict your possibilities (opportunities) tomorrow."

-Richard Hamming

Hoping to see you all  soon

Feel free to ask any questions.

Image Credits:

https://flaticon.com

https://www.flaticon.com/authors/photo3idea-studio

https://www.freepik.com

https://www.flaticon.com/authors/smashicons

https://giphy.com

https://www.flaticon.com/authors/srip

https://www.flaticon.com/authors/flat-icons

https://www.flaticon.com/Nikita Golubev

https://mathworks.com

https://scikit-learn.org/stable/auto_examples/applications/plot_face_recognition.html

https://forbes.com

Machine Learning Techniques

&

Machine Learning Practices

Orientation

An Interactive Session

Faculty

 Ashish (Vijay) Tendulkar

Machine Learning Specialist (Google)

 Machine learning,

and Deep learning  with applications to Natural Language Processing

Instructors

Anamika

Abhinandan

Arun

Amrutha

Jimmi

Swarnim

Debajyoti

Nitin

Instructors

Anamika

Arun

Amrutha

Karthik

Swarnim

Debajyoti

Nitin

Jimmi

ML Techniques

Regression

Classification

Clustering

1

An  Introduction 

ML Techniques

Regression

  1. Linear

  2. Polynomial

  3. Regularization

2-3

ML Techniques

Classification

  1. Least Square

  2. Perceptron

  3. Naive Bayes

4-6

Sepal

Petal

ML Techniques

Classification

  1.  KNN

  2. Linear SVM

  3. NonLinear SVM

7-8

Sepal

Petal

ML Techniques

Classification

  1. Decision Tree

  2. Bagging

  3. Boosting

9-10

Sepal

Petal

ML Techniques

Clustering

  1. K-Means

  2. HCA

11

ML Techniques

Classification

  1. Neural Networks

  2. Back Propagation

12

Sepal

Petal

Does this course have any programming Components?

def loss(X, w, y):
  y_hat = predict(X, w)
  samp_loss = np.maximum(-1*y_hat*y, np.zeros(y.shape[0])))
  J = np.sum(samp_loss)
  return J

What is the Grading Policy?

Two Quizzes

Final Exam

Types of Questions:

1. MCQ

2. MSQ

3. NAT

4.Programming

Two Proctored Programming Exam

Machine Learning Practice 

MLF

MLT

MLP

Make a hot & sweet drink:

 How do you select the required ingredients? How do you mix? Does order of mixing matter? How do you assess the quality? ...

All about ingredients.

Essential and inevitable!

Everything is trivial in cook books

Reading a cook book

Our Kitchen

from sklearn import datasets
from sklearn import pipeline
from sklearn import linear_model
from sklearn import metrics

Feel free to ask any questions.