ML Math Q&A: Derivatives ML Algorithms | Cosine vs Euclidean Distance | Cohere Labs ML Summer School

Welcome to this Machine Learning Math Q&A, a follow-up to the ML Math Refresher I taught live for Cohere Lab’s ML Summer School! This session dives deeper into some of the most commonly asked questions from the live event.

📌 In this video, I answer two foundational questions:

1️⃣ How are derivatives used in classical machine learning algorithms like clustering, decision trees, and more?
2️⃣ When should you use cosine similarity vs Euclidean distance in ML models and vector comparisons?

Key Moments
00:05 ML Math Refresher Overview
02:47 Question 1
03:29 K-Means Algorithm
04:58 Decision Trees
06:37 Support Vector Machine
07:10 Naive Bayes
9:59 Question 2
12:06 What is Cosine Similarity?
14:50 What is Euclidean Distance?

These concepts are critical to understanding how machine learning models function mathematically, even beyond neural networks—especially in unsupervised learning, tree-based models, and embedding-based similarity tasks.

🧠 Topics Reviewed from the Full Session:
✅Derivatives and gradients in optimization
✅Partial derivatives for multivariate functions
✅Cartesian vectors and similarity metrics
✅Cosine similarity vs Euclidean distance
✅Eigenvalues and eigenvectors and their ML relevance (e.g. PCA, spectral clustering)

🎥 Watch the full Machine Learning Math Refresher session hosted by Cohere Labs
👉 https://sites.google.com/cohere.com/coherelabs-community/community-programs/summer-school
👉 It covers all the foundational math you need for ML: derivatives, vectors, gradients, distance metrics, and eigen analysis.

📅 Stay Connected:
✅ Don’t forget to subscribe for more clear, visual math explanations
✅ Check out the other videos on my channel for in-depth tutorials on each of these topics
✅ Join the live bi-weekly Machine Learning Math sessions hosted by me at Cohere Labs—we break down core concepts and take live questions in real time!

👨‍💻 Perfect For:
- ML engineers and researchers
- Data science students
- ML summer school attendees
- Anyone brushing up on the math behind ML models
- Developers entering machine learning

📢Be sure to checkout the full math playlists here to ace your exam!
➡️DERIVATIVES: https://www.youtube.com/playlist?list=PLcw2oRu6_BxuBVJUOx0sHPdToiSKlgCBn
➡️LINEAR ALGEBRA: https://www.youtube.com/playlist?list=PLcw2oRu6_Bxs-xv2TaR1TcNcXbhpMuc0S

📢 Follow me on Instagram and TikTok for more fun math videos & facts!
➡️https://www.instagram.com/mathunlockedwithkatrina/
➡️https://www.tiktok.com/@mathunlockedwithkatrina

This video is a machine learning math Q&A lecture as part of my math series about derivatives, linear algebra and machine learning. This video is a follow up to the ML Math Refresher as part of Cohere Lab's ML Summer School. Subscribe to my channel if you want to learn more about math and machine learning math tricks!

#maths #math #mathematics #machinelearning #artificialintelligence #datascience #coherelabs #machinelearningmodels #mathematician #education #stem #stemeducation #mathunlockedwithkatrina #mathskills #mathclass #mathmadeeasy #mathhacks #mathtricks #mathchallenge #trending #educational #universitymath #collegemath #highschoolmath #satprep #greprep #grepreparation #mathlover #mathhelp #mathstudent #mathgenius #mathfun #mathproblems #mathtutorial #mathmotivation #learningmath #mathforfun #mathvideos #mathislife #mathteacher #mathslover #apcalculus #actmath #mathpractice #studygram #studyhacks #studywithme #mathconcepts #mathsolving #mathexam #mathsquad #stemlearning #mathskillsdaily #quickmath #mathlearning #mathcommunity #mathresources #cosinefunction #euclidean #viralvideo #foryou #fyp

Видео ML Math Q&A: Derivatives ML Algorithms | Cosine vs Euclidean Distance | Cohere Labs ML Summer School канала Math Unlocked With Katrina