Machine learning roadmap
Layer 1 · Foundations
Layer 2 · Core ML
Layer 3 · Deep learning
Layer 4 · Language
Layer 5 · Vision
Layer 1 · Foundations
- Start
- Implement Dot ProductEasy
- Implement Cosine SimilarityEasy
- Matrix TransposeEasy
- Mean, Median, ModeEasy
- Sample Variance & Standard DeviationEasy
- Expected Value (Discrete Distribution)Easy
- Bernoulli Probability Mass Function & MomentsEasy
- Binomial Probability Mass FunctionEasy
- Compute Covariance MatrixEasy
- Implement Matrix NormalizationMedium
- Compute Pearson Correlation MatrixMedium
- Calculate Eigenvalues of a MatrixMedium
- Poisson Probability Mass Function & Cumulative Distribution FunctionMedium
- One-Sample t-TestMedium
- Matrix InverseMedium
- Bootstrap Mean & Confidence IntervalMedium
- PCA ProjectionHard
About this roadmap
TensorTonic 125 is a path of 125 problems across 13 topics: Math Foundations for ML, Data Preprocessing & Feature Engineering, Optimization, Losses & Activation Functions, Classical ML, Neural Networks, Metrics & Evaluation, Sequence Models, NLP & LLM Basics, Transformer Paper, BERT Paper, Word2Vec Paper, ResNet Paper and Vision Transformer Paper. Start at the top and work down, because each topic builds on the ones above it. Click a topic to see its problems and open any of them to solve it in the browser.
Who is it for?
- New to TensorTonic and not sure where to start
- Building strong ML fundamentals
- Students preparing for ML related interviews
- Learning on the free plan