Machine Learning Mathematics Roadmap — How much math is required?
Linear Algebra, Statistics, Probability, Objective Functions,
Regularization, Information Theory, Optimization, Distribution
Contents
FREE Resources -
Chapter 1 — Linear Algebra
Chapter 2 — Statistics
Chapter 3 — Probability
Chapter 4 — Objective Functions
Chapter 5 — Regularization
Chapter 6 — Information Theory
Chapter 7 — Optimization
Chapter 8 — Distribution
This phase is different from books that are available on the internet. I included all the topics required to understand the whole architecture of Machine Learning algorithms.
Examples of how and where these mathematical equations are used and Interview Questions can be asked of an ML Engineer while hiring.
We will learn different concepts individually, converting mathematical equations into Python programming expressions along with their examples in the real world.
FREE Resources →
Mathematics for Machine Learning
Algebra, Topology, Differential Calculus, and Optimization Theory For Computer Science and Machine Learning
All math topics for Machine Learning by Stanford
Stanford CS229: Machine Learning Course | Summer 2019 (Anand Avati)
Chapter 1 — Linear Algebra
Learn for FREE — Mathematics for ML — Linear Algebra
Mathematics for Machine Learning — Linear Algebra
3 | Eigenvalues and Eigenvectors
4 | Singular Value Decomposition (SVD)
Chapter 2 — Statistics
The Element of Statistical Learning
Elements of Statistical Learning: data mining, inference, and prediction. 2nd Edition.
Statistics give us 2 tools descriptive and inferential
1 | Descriptive Statistics
2 | Inferential Statistics
6 | Analysis of Variance (ANOVA)
10 | Maximum Likelihood Estimation (MLE)
Chapter 3 — Probability
Probability Theory: The Logic of Science
https://bayes.wustl.edu/etj/prob/book.pdf
4 | Joint and Marginal Probabilities
5 | Independence and Conditional Independence
Chapter 4 — Objective Functions
4 | Binary Cross-Entropy (Log Loss)
6 | Maximum Likelihood Estimation (MLE)
7 | Sparse Categorical Cross-Entropy
9 | Kullback-Leibler Divergence
Chapter 5 — Regularization
1 | L1 Regularization (Lasso Regression)
2 | L2 Regularization (Ridge Regression)
3 | Elastic Net Regularization
10 | Total Variation Regularization
Chapter 6 — Information Theory
Information Theory, Inference and Learning Algorithms
David MacKay: Information Theory, Pattern Recognition and Neural Networks: The Book
5 | Relative Entropy (Kullback-Leibler Divergence)
Chapter 7 — Optimization
2 | Stochastic Gradient Descent (SGD)
3 | Mini-Batch Gradient Descent
5 | Nesterov Accelerated Gradient (NAG)
6 | Adagrad (Adaptive Gradient Algorithm)
7 | RMSprop (Root Mean Square Propagation)
8 | Adam (Adaptive Moment Estimation)
Chapter 8 — Distribution
4 | Normal (Gaussian) Distribution
Calculus
Calculus 1 | Math | Khan Academy
Machine Learning, MLOps & GenerativeAI Roadmap
September ML Cohort 2023
WhatsApp for Chat or Quick Call
Want to join the Live Cohort Ping me Hi here: https://wa.me/919074919189
PS: Be part of the closed community, it’s the last cohort in 2023, Build a Strong Machine Learning Portfolio/Personal Brand.
Act now.
Limited seats.
Registration will end on 31st August 2023.
Are you working in a Leadership position and want to learn about AI/ML and Generative AI?
Customized Roadmap for your specific needs
Ping me “I am a Leader” on WhatsApp (+91 9074919189)
OR
click here: https://wa.link/7cnkyr
Share your requirements with me at connect@himanshuramchandani.co
I will customize the roadmap for you.
Session Structure →
- Topic Understanding
- Real-world examples
- Implementation in Python
- Interview questions on that topic
- Questions to implement in programming
- Reading one blog or reacting on the resource in the machine learning space
- Study one company hiring in Machine Learning at a time, and analyze their products and services.
- Discussion on How to be better?
About me (Your Mentor)
I am Himanshu Ramchandani a Data & Engineering Consultant. I help enterprises utilize big data to build AI-powered products & Mentor professionals to improve their skills in the data field by 1% every day.
the epoch → an AI Newsletter
→ Leverage Data, Products & AI in 3 min.
→ Top 2 AI news & developments.
→ 1 Action Tip from Experts in BigData Analytics, Data Engg & ML.
→ AI Investments.
→ Career & Jobs.
Join the tribe of 20,000+ Entrepreneurs, Tech Leaders, Data Professionals & Devs.