Kickstart Machine Learning, understand maths behind essential algorithms, implement them in python & build 8+ projects!
InstructorMohit Uniyal
The curriculum includes specific lessons for implementing algorithms from scratch, such as Gradient Descent and Logistic Regression training loops.
Lessons cover essential mathematical concepts including Loss/Error Functions and Bayes Theorem derivation.
Editorial course preview
These 4 complementary views highlight concrete, legible examples from the course presentation.
A white slide titled ML Techniques from scratch lists algorithms such as Linear Regression and Neural Networks beside a laptop displaying code
A course slide titled Course Projects lists eight machine learning tasks beside a white humanoid robot and a small presenter overlay.
Course slide outlining fundamental machine learning problems, categorizing supervised and unsupervised learning methods with a presenter overlay.
Course slide listing machine learning topics such as Convex Optimisation and Bias Variance Tradeoff, featuring a robot image and presenter inset.
One signal suggests the speed of mathematical derivations can be difficult to follow for some learners. This review was created before the displayed update date, and while an update label is present, it does not prove a correction has been made.
A signal indicates that certain code segments may require updates due to deprecation.
The curriculum aligns with the stated goals of programmers and students interested in machine learning fundamentals.