Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

https://ecesocbitmesra.

in/

Machine Learning Course Structure

Week-1

1. Installing Python:
https://youtu.be/OCHtT4wJdNA

2. Datasets and types:


https://youtu.be/32OTiLq3TFQ

Source to find datasets:


https://www.kaggle.com/datasets

3. Using Pandas(to explore and clean data):


Comprehensive:
https://www.youtube.com/playlist?list=PL-osiE80TeTsWmV9i9c58mdDCSskIFdDS
Fast: https://www.kaggle.com/learn/pandas

4. Data Preprocessing:
https://youtu.be/9uvIazKs2uI

Week-2

1. Implementing traditional machine learning algorithms in python using scikit-learn:


https://www.youtube.com/watch?v=0B5eIE_1vpU
(Tutorial has a section on ml specific data preprocessing)

2. Some algorithms to consider implementing in your project:


Decision Trees
https://www.youtube.com/watch?v=qDcl-FRnwSU
Random Forest
https://www.youtube.com/watch?v=ok2s1vV9XW0
Support Vector Machines
https://www.youtube.com/watch?v=FB5EdxAGxQg
Naive Bayes
https://www.youtube.com/watch?v=O2L2Uv9pdDA

/*You can also refer Algorithms of your choice from YouTube it’s completely up to you */
https://ecesocbitmesra.in/

Week-3

1. OpenCV(usage and introduction): https://www.youtube.com/watch?v=oXlwWbU8l2o


For recognition systems.
Can go on to implement Deep Learning models on the image/video cleaned.

Neural Networks :
Convolutional Neural Network(CNN): https://youtu.be/zfiSAzpy9NM
CNN implementation using TensorFlow(Follow along the video to understand code implementation) :
https://www.youtube.com/watch?v=7HPwo4wnJeA

Example Project Ideas:-

1.Recognisation and Prediction


Movie Prediction
Music Recommendation
Vehicle price predictor
Weather Forecasting
Handwriting to text convertor

2.Security System
Fraud detection system
Fake news detection

3.Health and Safety System


Prediction of disease (Diabetes)
Suggesting best Doctors nearby
BMI Calculator
Waste management

** Contact mentors in the group for any further guidance!!!

LEARN GOOD AND BE CREATIVE!!


ALL THE BEST!!

You might also like