NOTES ML
Define Goal : PRODUCTS or ALGORITHMS
1. Maths
Linear Algebra (Matrix, Vector)
Statistics
Probability
2. Learn Python & its Libraries
Numpy
Pandas
3. Learn ML Algorithms
Supervised vs Unsupervised vs Reinforcement
Linear Regression, Logistic Regression, Clustering
KNN (K Nearest Neighbours)
SVM (Support Vector Machine)
Decision Trees
Random Forests
Overfitting, Underfitting
Regularization, Gradient Descent, Slope
Confusion Matrix
4. Data Preprocessing (for higher accuracy)
Handling Null Values
Standardization
Handling Categorical Values
One-Hot Encoding
Feature Scaling
5. Learn ML libraries
Scikit learn
Matplotlib
Tensorflow for DL
6. Practice, Practice, Practice (Kaggle)
Machine learning Adrew NG
[Link]
v=vStJoetOxJg&list=PLkDaE6sCZn6FNC6YRfRQc_F
beQrF8BwGI
[Link]
algorithms?specialization=machine-learning-
introduction
[Link]
============
[Link]
training-deep-learning-23753149/introduction-to-the-
dl-training-process?resume=false&u=57692769. —
good to start with
[Link] —
Simple Fine tuning of a model
[Link]
[Link]
generation-with-python/training-the-t5-small-model?
resume=false&u=57692769 — Trainign the Model
[Link]
— Feature engineering
[Link]
v=Q9zv369Ggfk&t=11s — fine tuninng and
knowledge base
Certifications
AI Product Manager Nanodegree - Udacity
Certified Scrum Product Owner (CSPO)
Certified AI Specialist - Coursera
Professional Affiliations
Member, Product Management Institute
Member, AI Product Managers Association
====================================
Reseach paper from Linked in top voices
[Link] — RAG